{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,28]],"date-time":"2026-07-28T21:18:19Z","timestamp":1785273499125,"version":"3.55.0"},"reference-count":461,"publisher":"Emerald","issue":"2","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,1,25]]},"abstract":"<jats:p>Deep learning has become the dominant approach in addressing various tasks in Natural Language Processing (NLP). Although text inputs are typically represented as a sequence of tokens, there is a rich variety of NLP problems that can be best expressed with a graph structure. As a result, there is a surge of interest in developing new deep learning techniques on graphs for a large number of NLP tasks. In this survey, we present a comprehensive overview on Graph Neural Networks (GNNs) for Natural Language Processing. We propose a new taxonomy of GNNs for NLP, which systematically organizes existing research of GNNs for NLP<\/jats:p>","DOI":"10.1561\/2200000096","type":"journal-article","created":{"date-parts":[[2023,1,25]],"date-time":"2023-01-25T04:56:46Z","timestamp":1674622606000},"page":"119-328","source":"Crossref","is-referenced-by-count":242,"title":["Graph Neural Networks for Natural Language Processing: A Survey"],"prefix":"10.1108","volume":"16","author":[{"given":"Lingfei","family":"Wu","sequence":"first","affiliation":[{"name":"JD.COM Silicon Valley Research Center ,","place":["USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Chen","sequence":"additional","affiliation":[{"name":"Rensselaer Polytechnic Institute ,","place":["USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kai","family":"Shen","sequence":"additional","affiliation":[{"name":"Zhejiang University ,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaojie","family":"Guo","sequence":"additional","affiliation":[{"name":"JD.COM Silicon Valley Research Center ,","place":["USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hanning","family":"Gao","sequence":"additional","affiliation":[{"name":"Central China Normal University ,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shucheng","family":"Li","sequence":"additional","affiliation":[{"name":"Nanjing University National Key Lab for Novel Software Technology, ,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jian","family":"Pei","sequence":"additional","affiliation":[{"name":"Simon Fraser University ,","place":["Canada"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bo","family":"Long","sequence":"additional","affiliation":[{"name":"JD.COM, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"140","published-online":{"date-parts":[[2023,1,25]]},"reference":[{"issue":"1","key":"2026033012312262700_ref001","first-page":"6446","article-title":"Community detection and stochastic block models: recent developments","volume":"18","author":"Abbe","year":"2017","journal-title":"The Journal of Machine Learning Research"},{"key":"2026033012312262700_ref002","doi-asserted-by":"crossref","DOI":"10.14569\/IJACSA.2017.081052","article-title":"Text summarization techniques: a brief survey","volume-title":"arXiv preprint","author":"Allahyari","year":"2017"},{"key":"2026033012312262700_ref003","volume-title":"Learning to Represent Programs with Graphs","author":"Allamanis","year":"2018"},{"key":"2026033012312262700_ref004","article-title":"code2seq: Generating sequences from structured representations of code","volume-title":"arXiv preprint","author":"Alon","year":"2018"},{"key":"2026033012312262700_ref005","volume-title":"Tree-structured decoding with doubly-recurrent neural networks","author":"Alvarez-Melis","year":"2016"},{"key":"2026033012312262700_ref006","article-title":"Mathqa: Towards interpretable math word problem solving with operation-based formalisms","volume-title":"arXiv preprint","author":"Amini","year":"2019"},{"key":"2026033012312262700_ref007","doi-asserted-by":"publisher","first-page":"2442","DOI":"10.18653\/v1\/P16-1231","volume-title":"Globally Normalized Transition-Based Neural Networks","author":"Andor","year":"2016"},{"key":"2026033012312262700_ref008","doi-asserted-by":"publisher","first-page":"344","DOI":"10.3115\/v1\/P15-1034","volume-title":"Leveraging Linguistic Structure For Open Domain Information Extraction","author":"Angeli","year":"2015"},{"key":"2026033012312262700_ref009","volume-title":"Diffusion-Convolutional Neural Networks","author":"Atwood","year":"2016"},{"key":"2026033012312262700_ref010","article-title":"Layer normalization","volume-title":"arXiv preprint","author":"Ba","year":"2016"},{"key":"2026033012312262700_ref011","volume-title":"Neural Machine Translation by Jointly Learning to Align and Translate","author":"Bahdanau","year":"2015"},{"key":"2026033012312262700_ref012","first-page":"4430","volume-title":"Semantic Representation for Dialogue Modeling","author":"Bai","year":"2021"},{"key":"2026033012312262700_ref013","doi-asserted-by":"publisher","first-page":"1206","DOI":"10.18653\/v1\/2020.emnlp-main.92","volume-title":"Online Back-Parsing for AMR-to-Text Generation","author":"Bai","year":"2020"},{"key":"2026033012312262700_ref014","first-page":"4387","volume-title":"A2N: attending to neighbors for knowledge graph inference","author":"Bansal","year":"2019"},{"key":"2026033012312262700_ref015","volume-title":"Table-to-text: Describing table region with natural language","author":"Bao","year":"2018"},{"key":"2026033012312262700_ref016","article-title":"A parallel corpus of Python functions and documentation strings for automated code documentation and code generation","volume-title":"arXiv preprint","author":"Barone","year":"2017"},{"key":"2026033012312262700_ref017","doi-asserted-by":"publisher","first-page":"1957","DOI":"10.18653\/v1\/D17-1209","volume-title":"Graph Convolutional Encoders for Syntax-aware Neural Machine Translation","author":"Bastings","year":"2017"},{"key":"2026033012312262700_ref018","doi-asserted-by":"publisher","first-page":"273","DOI":"10.18653\/v1\/P18-1026","volume-title":"Graph-to-Sequence Learning using Gated Graph Neural Networks","author":"Beck","year":"2018"},{"key":"2026033012312262700_ref019","first-page":"273","volume-title":"Graph-to-Sequence Learning using Gated Graph Neural Networks","author":"Beck","year":"2018"},{"key":"2026033012312262700_ref020","first-page":"11711179","volume-title":"Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks","author":"Bengio","year":"2015"},{"issue":"2","key":"2026033012312262700_ref021","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/1667053.1667056","article-title":"The nested chinese restaurant process and bayesian nonparametric inference of topic hierarchies","volume":"57","author":"Blei","year":"2010","journal-title":"Journal of the ACM (JACM"},{"key":"2026033012312262700_ref022","first-page":"993","article-title":"Latent dirichlet allocation","volume":"3","author":"Blei","year":"2003","journal-title":"the Journal of machine Learning research"},{"key":"2026033012312262700_ref023","first-page":"440","volume-title":"Biographies, bollywood, boom-boxes and blenders: Domain adaptation for sentiment classification","author":"Blitzer","year":"2007"},{"key":"2026033012312262700_ref024","doi-asserted-by":"publisher","first-page":"4560","DOI":"10.18653\/v1\/P19-1448","volume-title":"Representing Schema Structure with Graph Neural Networks for Text-to-SQL Parsing","author":"Bogin","year":"2019"},{"key":"2026033012312262700_ref025","doi-asserted-by":"publisher","first-page":"3659","DOI":"10.18653\/v1\/D19-1378","volume-title":"Global Reasoning over Database Structures for Text-to-SQL Parsing","author":"Bogin","year":"2019"},{"key":"2026033012312262700_ref026","article-title":"Large-scale simple question answering with memory networks","volume-title":"arXiv preprint","author":"Bordes","year":"2015"},{"key":"2026033012312262700_ref027","first-page":"1","volume-title":"Translating embeddings for modeling multi-relational data","author":"Bordes","year":"2013"},{"key":"2026033012312262700_ref028","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/D15-1075","article-title":"A large annotated corpus for learning natural language inference","volume-title":"arXiv preprint","author":"Bowman","year":"2015"},{"key":"2026033012312262700_ref029","article-title":"Language models are few-shot learners","volume-title":"arXiv preprint","author":"Brown","year":"2020"},{"key":"2026033012312262700_ref030","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/D18-1547","volume-title":"MultiWOZ-A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modelling","author":"Budzianowski","year":"2018"},{"key":"2026033012312262700_ref031","doi-asserted-by":"publisher","first-page":"1290","DOI":"10.18653\/v1\/2020.acl-main.119","volume-title":"AMR Parsing via Graph-Sequence Iterative Inference","author":"Cai","year":"2020"},{"key":"2026033012312262700_ref032","first-page":"7464","volume-title":"Graph Transformer for Graph-to-Sequence Learning","author":"Cai","year":"2020"},{"issue":"05","key":"2026033012312262700_ref033","doi-asserted-by":"publisher","first-page":"7464","DOI":"10.1609\/aaai.v34i05.6243","article-title":"Graph Transformer for Graph-to-Sequence Learning","volume":"34","author":"Cai","year":"2020","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"2026033012312262700_ref034","first-page":"748","volume-title":"Smatch: an Evaluation Metric for Semantic Feature Structures","author":"Cai","year":"2013"},{"key":"2026033012312262700_ref035","volume-title":"Conversational qa for faqs","author":"Campos","year":"2019"},{"key":"2026033012312262700_ref036","first-page":"2306","volume-title":"Question Answering by Reasoning Across Documents with Graph Convolutional Networks","author":"Cao","year":"2019"},{"key":"2026033012312262700_ref037","first-page":"1452","volume-title":"Multi-Channel Graph Neural Network for Entity Alignment","author":"Cao","year":"2019"},{"key":"2026033012312262700_ref038","first-page":"357","volume-title":"BAG: Bi-directional Attention Entity Graph Convolutional Network for Multi-hop Reasoning Question Answering","author":"Cao","year":"2019"},{"key":"2026033012312262700_ref039","first-page":"29","article-title":"A Benchmarking Environment for Reinforcement Learning Based Task Oriented Dialogue Management","volume":"1050","author":"Casanueva","year":"2017","journal-title":"stat"},{"key":"2026033012312262700_ref040","first-page":"5596","volume-title":"Inducing target-specific latent structures for aspect sentiment classification","author":"Chen","year":"2020"},{"key":"2026033012312262700_ref041","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/P17-1171","article-title":"Reading wikipedia to answer open-domain questions","volume-title":"arXiv preprint","author":"Chen","year":"2017"},{"issue":"2","key":"2026033012312262700_ref042","doi-asserted-by":"crossref","first-page":"25","DOI":"10.1145\/3166054.3166058","article-title":"A survey on dialogue systems: Recent advances and new frontiers","volume":"19","author":"Chen","year":"2017","journal-title":"Acm Sigkdd Explorations Newsletter"},{"key":"2026033012312262700_ref043","first-page":"4946","volume-title":"The bq corpus: A large-scale domain-specific chinese corpus for sentence semantic equivalence identification","author":"Chen","year":"2018"},{"key":"2026033012312262700_ref044","first-page":"7521","volume-title":"Schema-Guided Multi-Domain Dialogue State Tracking with Graph Attention Neural Networks","author":"Chen","year":"2020"},{"key":"2026033012312262700_ref045","first-page":"1257","volume-title":"Structured Dialogue Policy with Graph Neural Networks","author":"Chen","year":"2018"},{"key":"2026033012312262700_ref046","first-page":"6152","volume-title":"Neural Graph Matching Networks for Chinese Short Text Matching","author":"Chen","year":"2020"},{"key":"2026033012312262700_ref047","article-title":"Neural natural language inference models enhanced with external knowledge","volume-title":"arXiv preprint","author":"Chen","year":"2017"},{"key":"2026033012312262700_ref048","first-page":"8635","volume-title":"KGPT: Knowledge-Grounded Pre-Training for Data-to-Text Generation","author":"Chen","year":"2020"},{"key":"2026033012312262700_ref049","doi-asserted-by":"publisher","first-page":"3667","DOI":"10.18653\/v1\/2020.acl-main.338","volume-title":"Aspect Sentiment Classification with Document-level Sentiment Preference Modeling","author":"Chen","year":"2020"},{"key":"2026033012312262700_ref050","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/N19-1299","volume-title":"Bidirectional Attentive Memory Networks for Question Answering over Knowledge Bases","author":"Chen","year":"2019"},{"key":"2026033012312262700_ref051","volume-title":"Iterative Deep Graph Learning for Graph Neural Networks: Better and Robust Node Embeddings","author":"Chen","year":"2020"},{"key":"2026033012312262700_ref052","article-title":"Toward Subgraph Guided Knowledge Graph Question Generation with Graph Neural Networks","volume-title":"arXiv preprint","author":"Chen","year":"2020"},{"key":"2026033012312262700_ref053","first-page":"1230","volume-title":"GraphFlow: Exploiting Conversation Flow with Graph Neural Networks for Conversational Machine Comprehension","author":"Chen","year":"2020"},{"key":"2026033012312262700_ref054","volume-title":"Reinforcement Learning Based Graph-to-Sequence Model for Natural Question Generation","author":"Chen","year":"2020"},{"key":"2026033012312262700_ref055","first-page":"85","volume-title":"Kate: K-competitive autoencoder for text","author":"Chen","year":"2017"},{"key":"2026033012312262700_ref056","doi-asserted-by":"publisher","first-page":"1724","DOI":"10.3115\/v1\/d14-1179","volume-title":"Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation","author":"Cho","year":"2014"},{"key":"2026033012312262700_ref057","first-page":"2174","volume-title":"QUAC: Question answering in context","author":"Choi","year":"2020"},{"key":"2026033012312262700_ref058","volume-title":"Rethinking Attention with Performers","author":"Choromanski","year":"2021"},{"key":"2026033012312262700_ref059","first-page":"1163","volume-title":"Towards coherent multi-document summarization","author":"Christensen","year":"2013"},{"key":"2026033012312262700_ref060","doi-asserted-by":"publisher","first-page":"4925","DOI":"10.18653\/v1\/D19-1498","volume-title":"Connecting the Dots: Document-level Neural Relation Extraction with Edge-oriented Graphs","author":"Christopoulou","year":"2019"},{"key":"2026033012312262700_ref061","first-page":"704","volume-title":"Query expansion using random walk models","author":"Collins-Thompson","year":"2005"},{"key":"2026033012312262700_ref062","first-page":"1406","volume-title":"MuTual: A Dataset for Multi-Turn Dialogue Reasoning","author":"Cui","year":"2020"},{"key":"2026033012312262700_ref063","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/2020.coling-main.468","article-title":"Enhancing Extractive Text Summarization with Topic-Aware Graph Neural Networks","volume-title":"arXiv preprint","author":"Cui","year":"2020"},{"key":"2026033012312262700_ref064","doi-asserted-by":"publisher","first-page":"2329","DOI":"10.18653\/v1\/2020.findings-emnlp.211","volume-title":"Edge-Enhanced Graph Convolution Networks for Event Detection with Syntactic Relation","author":"Cui","year":"2020"},{"key":"2026033012312262700_ref065","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/P17-1055","volume-title":"Attention-over-Attention Neural Networks for Reading Comprehension","author":"Cui","year":"2017"},{"key":"2026033012312262700_ref066","doi-asserted-by":"crossref","DOI":"10.3115\/1075812.1075823","volume-title":"Expanding the Scope of the ATIS Task: The ATIS-3 Corpus","author":"Dahl","year":"1994"},{"key":"2026033012312262700_ref067","doi-asserted-by":"publisher","first-page":"3649","DOI":"10.18653\/v1\/N19-1366","volume-title":"Structural Neural Encoders for AMR-to-text Generation","author":"Damonte","year":"2019"},{"key":"2026033012312262700_ref068","volume-title":"Question answering by reasoning across documents with graph convolutional networks","author":"De Cao","year":"2018"},{"key":"2026033012312262700_ref069","first-page":"29","article-title":"Convolu-tional neural networks on graphs with fast localized spectral filtering","volume-title":"Advances in neural information processing systems","author":"Defferrard","year":"2016"},{"key":"2026033012312262700_ref070","volume-title":"Con-volutional 2d knowledge graph embeddings","author":"Dettmers","year":"2018"},{"key":"2026033012312262700_ref071","first-page":"1811","volume-title":"Convo-lutional 2D Knowledge Graph Embeddings","author":"Dettmers","year":"2018"},{"key":"2026033012312262700_ref072","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","volume-title":"arXiv preprint","author":"Devlin","year":"2018"},{"key":"2026033012312262700_ref073","doi-asserted-by":"publisher","first-page":"4171","DOI":"10.18653\/v1\/N19-1423","volume-title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","author":"Devlin","year":"2019"},{"key":"2026033012312262700_ref074","first-page":"2694","volume-title":"Cognitive Graph for Multi-Hop Reading Comprehension at Scale","author":"Ding","year":"2019"},{"key":"2026033012312262700_ref075","doi-asserted-by":"publisher","first-page":"1462","DOI":"10.18653\/v1\/P19-1141","volume-title":"A Neural Multi-digraph Model for Chinese NER with Gazetteers","author":"Ding","year":"2019"},{"key":"2026033012312262700_ref076","doi-asserted-by":"publisher","first-page":"4123","DOI":"10.18653\/v1\/2020.acl-main.379","volume-title":"Neural Reranking for Dependency Parsing: An Evaluation","author":"Do","year":"2020"},{"key":"2026033012312262700_ref077","first-page":"750","volume-title":"Graph transformation policy network for chemical reaction prediction","author":"Do","year":"2019"},{"key":"2026033012312262700_ref078","doi-asserted-by":"publisher","first-page":"33","DOI":"10.18653\/v1\/P16-1004","volume-title":"Language to Logical Form with Neural Attention","author":"Dong","year":"2016"},{"key":"2026033012312262700_ref079","doi-asserted-by":"crossref","DOI":"10.3115\/v1\/P14-2009","volume-title":"Adaptive recursive neural network for target-dependent twitter sentiment classification","author":"Dong","year":"2014"},{"key":"2026033012312262700_ref080","article-title":"Deep biaffine attention for neural dependency parsing","volume-title":"arXiv preprint","author":"Dozat","year":"2016"},{"key":"2026033012312262700_ref081","volume-title":"Learning to Ask: Neural Question Generation for Reading Comprehension","author":"Du","year":"2017"},{"key":"2026033012312262700_ref082","first-page":"2368","volume-title":"DROP: A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphs","author":"Dua","year":"2019"},{"key":"2026033012312262700_ref083","first-page":"2769","volume-title":"Semantic graph parsing with recurrent neural network DAG grammars","author":"Fancellu","year":"2019"},{"key":"2026033012312262700_ref084","first-page":"8823","volume-title":"Hierarchical Graph Network for Multi-hop Question Answering","author":"Fang","year":"2020"},{"key":"2026033012312262700_ref085","first-page":"8823","volume-title":"Hierarchical Graph Network for Multi-hop Question Answering","author":"Fang","year":"2020"},{"key":"2026033012312262700_ref086","doi-asserted-by":"crossref","first-page":"2427","DOI":"10.1109\/TASLP.2020.3016127","article-title":"Cross-lingual semantic role labeling with model transfer","volume":"28","author":"Fei","year":"2020","journal-title":"IEEE\/ACM Transactions on Audio, Speech, and Language Processing"},{"key":"2026033012312262700_ref087","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/2020.emnlp-main.99","article-title":"Scalable Multi-Hop Relational Reasoning for Knowledge-Aware Question Answering","volume-title":"arXiv preprint","author":"Feng","year":"2020"},{"key":"2026033012312262700_ref088","first-page":"1295","volume-title":"Scalable Multi-Hop Relational Reasoning for Knowledge-Aware Question Answering","author":"Feng","year":"2020"},{"key":"2026033012312262700_ref089","volume-title":"Structured Neural Summarization","author":"Fernandes","year":"2019"},{"key":"2026033012312262700_ref090","doi-asserted-by":"publisher","first-page":"7365","DOI":"10.18653\/v1\/2020.acl-main.657","volume-title":"Premise Selection in Natural Language Mathematical Texts","author":"Ferreira","year":"2020"},{"key":"2026033012312262700_ref091","article-title":"Fast graph representation learning with PyTorch Geometric","volume-title":"arXiv preprint","author":"Fey","year":"2019"},{"key":"2026033012312262700_ref092","first-page":"1426","volume-title":"A discriminative graph-based parser for the abstract meaning representation","author":"Flanigan","year":"2014"},{"key":"2026033012312262700_ref093","first-page":"1972","volume-title":"Learning Discrete Structures for Graph Neural Networks","author":"Franceschi","year":"2019"},{"key":"2026033012312262700_ref094","first-page":"4204","volume-title":"End-to-End AMR Coreference Resolution","author":"Fu","year":"2021"},{"key":"2026033012312262700_ref095","first-page":"1409","volume-title":"GraphRel: Modeling text as relational graphs for joint entity and relation extraction","author":"Fu","year":"2019"},{"key":"2026033012312262700_ref096","first-page":"3030","volume-title":"RDF-to-Text Generation with Graph-augmented Structural Neural Encoders","author":"Gao","year":"2020"},{"key":"2026033012312262700_ref097","first-page":"2743","volume-title":"Learning graph pooling and hybrid convolutional operations for text representations","author":"Gao","year":"2019"},{"key":"2026033012312262700_ref098","first-page":"294","volume-title":"Corpus expansion for statistical machine translation with semantic role label substitution rules","author":"Gao","year":"2011"},{"key":"2026033012312262700_ref099","doi-asserted-by":"publisher","first-page":"179","DOI":"10.18653\/v1\/P17-1017","volume-title":"Creating Training Corpora for NLG Micro-Planners","author":"Gardent","year":"2017"},{"key":"2026033012312262700_ref100","first-page":"1243","volume-title":"Convolutional sequence to sequence learning","author":"Gehring","year":"2017"},{"key":"2026033012312262700_ref101","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/D18-1443","article-title":"Bottom-up abstractive summarization","volume-title":"arXiv preprint","author":"Gehrmann","year":"2018"},{"key":"2026033012312262700_ref102","doi-asserted-by":"publisher","first-page":"3198","DOI":"10.18653\/v1\/2020.acl-main.292","volume-title":"KinGDOM: Knowledge-Guided DOMain Adaptation for Sentiment Analysis","author":"Ghosal","year":"2020"},{"key":"2026033012312262700_ref103","first-page":"1263","volume-title":"Neural message passing for quantum chemistry","author":"Gilmer","year":"2017"},{"key":"2026033012312262700_ref104","first-page":"45","volume-title":"Seeing stars when there aren\u2019t many stars: Graph-based semi-supervised learning for sentiment categorization","author":"Goldberg","year":"2006"},{"issue":"2","key":"2026033012312262700_ref105","doi-asserted-by":"crossref","first-page":"268","DOI":"10.1021\/acscentsci.7b00572","article-title":"Automatic chemical design using a data-driven continuous representation of molecules","volume":"4","author":"G\u00f3mez-Bombarelli","year":"2018","journal-title":"ACS central science"},{"key":"2026033012312262700_ref106","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/P16-1154","article-title":"Incorporating copying mechanism in sequence-to-sequence learning","volume-title":"arXiv preprint","author":"Gu","year":"2016"},{"key":"2026033012312262700_ref107","doi-asserted-by":"publisher","first-page":"1040","DOI":"10.18653\/v1\/D19-1096","volume-title":"A Lexicon-Based Graph Neural Network for Chinese NER","author":"Gui","year":"2019"},{"key":"2026033012312262700_ref108","article-title":"Deep graph translation","volume-title":"arXiv preprint","author":"Guo","year":"2018"},{"key":"2026033012312262700_ref109","first-page":"250","volume-title":"Deep multi-attributed graph translation with node-Edge Co-evolution","author":"Guo","year":"2019"},{"key":"2026033012312262700_ref110","doi-asserted-by":"publisher","first-page":"241","DOI":"10.18653\/v1\/P19-1024","volume-title":"Attention Guided Graph Convolutional Networks for Relation Extraction","author":"Guo","year":"2019"},{"issue":"Mar.","key":"2026033012312262700_ref111","doi-asserted-by":"publisher","first-page":"297","DOI":"10.1162\/tacl_a_00269","article-title":"Densely Connected Graph Convolutional Networks for Graph-to-Sequence Learning","volume":"7","author":"Guo","year":"2019","journal-title":"Transactions of the Association for Computational Linguistics"},{"key":"2026033012312262700_ref112","doi-asserted-by":"publisher","first-page":"378","DOI":"10.18653\/v1\/D19-1036","volume-title":"CaRe: Open Knowledge Graph Embeddings","author":"Gupta","year":"2019"},{"key":"2026033012312262700_ref113","first-page":"387","volume-title":"Robust textual inference via graph matching","author":"Haghighi","year":"2005"},{"key":"2026033012312262700_ref114","first-page":"1024","volume-title":"Inductive representation learning on large graphs","author":"Hamilton","year":"2017"},{"key":"2026033012312262700_ref115","article-title":"Representation learning on graphs: Methods and applications","volume-title":"arXiv preprint","author":"Hamilton","year":"2017"},{"key":"2026033012312262700_ref116","doi-asserted-by":"publisher","first-page":"1475","DOI":"10.18653\/v1\/2020.findings-emnlp.133","volume-title":"Open Domain Question Answering based on Text Enhanced Knowledge Graph with Hyper-edge Infusion","author":"Han","year":"2020"},{"key":"2026033012312262700_ref117","doi-asserted-by":"publisher","first-page":"125","DOI":"10.18653\/v1\/D17-1012","volume-title":"Neural Machine Translation with Source-Side Latent Graph Parsing","author":"Hashimoto","year":"2017"},{"key":"2026033012312262700_ref118","doi-asserted-by":"publisher","first-page":"517","DOI":"10.1145\/511446.511513","volume-title":"Topic-Sensitive PageRank","author":"Haveliwala","year":"2002"},{"key":"2026033012312262700_ref119","first-page":"2281","volume-title":"Integrating Graph Contextualized Knowledge into Pre-trained Language Models","author":"He","year":"2020"},{"key":"2026033012312262700_ref120","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/P18-2058","article-title":"Jointly predicting predicates and arguments in neural semantic role labeling","volume-title":"arXiv preprint","author":"He","year":"2018"},{"key":"2026033012312262700_ref121","first-page":"473","volume-title":"Deep semantic role labeling: What works and what\u2019s next","author":"He","year":"2017"},{"key":"2026033012312262700_ref122","article-title":"Deep convolutional networks on graph-structured data","volume-title":"arXiv preprint","author":"Henaff","year":"2015"},{"key":"2026033012312262700_ref123","volume-title":"Teaching Machines to Read and Comprehend","author":"Hermann","year":"2015"},{"key":"2026033012312262700_ref124","first-page":"192","volume-title":"OHSUMED: An interactive retrieval evaluation and new large test collection for research","author":"Hersh","year":"1994"},{"issue":"8","key":"2026033012312262700_ref125","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long short-term memory","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neural computation"},{"issue":"1","key":"2026033012312262700_ref126","first-page":"1303","article-title":"Stochastic variational inference","volume":"14","author":"Hoffman","year":"2013","journal-title":"The Journal of Machine Learning Research"},{"key":"2026033012312262700_ref127","first-page":"50","volume-title":"Probabilistic latent semantic indexing","author":"Hofmann","year":"1999"},{"key":"2026033012312262700_ref128","volume-title":"Convolutional Neural Network Architectures for Matching Natural Language Sentences","author":"Hu","year":"2014"},{"key":"2026033012312262700_ref129","doi-asserted-by":"publisher","first-page":"3505","DOI":"10.1145\/3394171.3413711","volume-title":"Multi-Modal Attentive Graph Pooling Model for Community Question Answer Matching","author":"Hu","year":"2020"},{"key":"2026033012312262700_ref130","first-page":"3505","volume-title":"Multi-modal Attentive Graph Pooling Model for Community Question Answer Matching","author":"Hu","year":"2020"},{"key":"2026033012312262700_ref131","doi-asserted-by":"publisher","first-page":"456","DOI":"10.1145\/3240508.3240626","volume-title":"Attentive Interactive Convolutional Matching for Community Question Answering in Social Multimedia","author":"Hu","year":"2018"},{"key":"2026033012312262700_ref132","doi-asserted-by":"publisher","first-page":"1157","DOI":"10.1145\/3343031.3350966","volume-title":"Hierarchical Graph Semantic Pooling Network for Multi-Modal Community Question Answer Matching","author":"Hu","year":"2019"},{"key":"2026033012312262700_ref133","first-page":"1157","volume-title":"Hierarchical graph semantic pooling network for multi-modal community question answer matching","author":"Hu","year":"2019"},{"key":"2026033012312262700_ref134","first-page":"4820","volume-title":"Heterogeneous Graph Attention Networks for Semi-supervised Short Text Classification","author":"Hu","year":"2019"},{"key":"2026033012312262700_ref135","article-title":"Strategies for pre-training graph neural networks","volume-title":"arXiv preprint","author":"Hu","year":"2019"},{"key":"2026033012312262700_ref136","first-page":"5010","volume-title":"GSN: A Graph-Structured Network for Multi-Party Dialogues","author":"Hu","year":"2019"},{"key":"2026033012312262700_ref137","first-page":"2704","volume-title":"Heterogeneous graph transformer","author":"Hu","year":"2020"},{"key":"2026033012312262700_ref138","doi-asserted-by":"publisher","first-page":"1091","DOI":"10.18653\/v1\/D18-1136","volume-title":"Parameterized Convolutional Neural Networks for Aspect Level Sentiment Classification","author":"Huang","year":"2018"},{"key":"2026033012312262700_ref139","doi-asserted-by":"publisher","first-page":"5469","DOI":"10.18653\/v1\/D19-1549","volume-title":"Syntax-Aware Aspect Level Sentiment Classification with Graph Attention Networks","author":"Huang","year":"2019"},{"key":"2026033012312262700_ref140","first-page":"11021","volume-title":"Location-Aware Graph Convolutional Networks for Video Question Answering","author":"Huang","year":"2020"},{"key":"2026033012312262700_ref141","first-page":"3442","volume-title":"Text Level Graph Neural Network for Text Classification","author":"Huang","year":"2019"},{"key":"2026033012312262700_ref142","doi-asserted-by":"publisher","first-page":"5094","DOI":"10.18653\/v1\/2020.acl-main.457","volume-title":"Knowledge Graph-Augmented Abstractive Summarization with Semantic-Driven Cloze Reward","author":"Huang","year":"2020"},{"key":"2026033012312262700_ref143","first-page":"581","volume-title":"Lexical semantic relatedness with random graph walks","author":"Hughes","year":"2007"},{"key":"2026033012312262700_ref144","doi-asserted-by":"publisher","first-page":"159","DOI":"10.18653\/v1\/D19-5319","volume-title":"Graph Enhanced Cross-Domain Text-to-SQL Generation","author":"Huo","year":"2019"},{"key":"2026033012312262700_ref145","doi-asserted-by":"publisher","first-page":"800","DOI":"10.18653\/v1\/2020.acl-main.73","volume-title":"Tree-Structured Neural Topic Model","author":"Isonuma","year":"2020"},{"key":"2026033012312262700_ref146","first-page":"2073","volume-title":"Summarizing source code using a neural attention model","author":"Iyer","year":"2016"},{"key":"2026033012312262700_ref147","article-title":"A survey on knowledge graphs: Representation, acquisition and applications","volume-title":"arXiv preprint","author":"Ji","year":"2020"},{"key":"2026033012312262700_ref148","doi-asserted-by":"publisher","first-page":"2475","DOI":"10.18653\/v1\/P19-1237","volume-title":"Graph-based Dependency Parsing with Graph Neural Networks","author":"Ji","year":"2019"},{"key":"2026033012312262700_ref149","doi-asserted-by":"publisher","first-page":"12","DOI":"10.18653\/v1\/P16-1002","volume-title":"Data Recombination for Neural Semantic Parsing","author":"Jia","year":"2016"},{"key":"2026033012312262700_ref150","doi-asserted-by":"publisher","first-page":"3622","DOI":"10.18653\/v1\/2020.emnlp-main.295","volume-title":"Neural Extractive Summarization with Hierarchical Attentive Heterogeneous Graph Network","author":"Jia","year":"2020"},{"key":"2026033012312262700_ref151","first-page":"151","volume-title":"Target-dependent twitter sentiment classification","author":"Jiang","year":"2011"},{"key":"2026033012312262700_ref152","first-page":"6281","volume-title":"A challenge dataset and effective models for aspect-based sentiment analysis","author":"Jiang","year":"2019"},{"key":"2026033012312262700_ref153","doi-asserted-by":"publisher","first-page":"4969","DOI":"10.18653\/v1\/D19-1502","volume-title":"Fine-Grained Entity Typing via Hierarchical Multi Graph Convolutional Networks","author":"Jin","year":"2019"},{"key":"2026033012312262700_ref154","first-page":"8026","volume-title":"SemSUM: Semantic Dependency Guided Neural Abstractive Summarization","author":"Jin","year":"2020"},{"issue":"05","key":"2026033012312262700_ref155","doi-asserted-by":"publisher","first-page":"8026","DOI":"10.1609\/aaai.v34i05.6312","article-title":"SemSUM: Semantic Dependency Guided Neural Abstractive Summarization","volume":"34","author":"Jin","year":"2020","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"2026033012312262700_ref156","first-page":"2004","volume-title":"Generalized Shortest-Paths Encoders for AMR-to-Text Generation","author":"Jin","year":"2020"},{"key":"2026033012312262700_ref157","first-page":"427","volume-title":"Bag of Tricks for Efficient Text Classification","author":"Joulin","year":"2017"},{"key":"2026033012312262700_ref158","volume-title":"Large Scale Graph Learning From Smooth Signals","author":"Kalofolias","year":"2019"},{"key":"2026033012312262700_ref159","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v34i05.6318","volume-title":"Infusing Knowledge into the Textual Entailment Task Using Graph Convolutional Networks","author":"Kapanipathi","year":"2020"},{"key":"2026033012312262700_ref160","first-page":"5156","volume-title":"Transformers are rnns: Fast autoregressive transformers with linear attention","author":"Katharopoulos","year":"2020"},{"key":"2026033012312262700_ref161","volume-title":"Scitail: A textual entailment dataset from science question answering","author":"Khot","year":"2018"},{"key":"2026033012312262700_ref162","doi-asserted-by":"publisher","first-page":"1746","DOI":"10.3115\/v1\/d14-1181","volume-title":"Convolutional Neural Networks for Sentence Classification","author":"Kim","year":"2014"},{"key":"2026033012312262700_ref163","first-page":"1989","volume-title":"LREC","author":"Kingsbury","year":"2002"},{"key":"2026033012312262700_ref164","doi-asserted-by":"publisher","first-page":"313","DOI":"10.1162\/tacl_a_00101","article-title":"Simple and Accurate Dependency Parsing Using Bidirectional LSTM Feature Representations","volume":"4","author":"Kiperwasser","year":"2016","journal-title":"Transactions of the Association for Computational Linguistics"},{"key":"2026033012312262700_ref165","article-title":"Semi-supervised classification with graph convolutional networks","volume-title":"arXiv preprint","author":"Kipf","year":"2016"},{"key":"2026033012312262700_ref166","volume-title":"Skip-Thought Vectors","author":"Kiros","year":"2015"},{"key":"2026033012312262700_ref167","volume-title":"Combining Neural Networks with Personalized PageRank for Classification on Graphs","author":"Klicpera","year":"2019"},{"key":"2026033012312262700_ref168","volume-title":"Tech. rep","author":"Knight","year":"2017"},{"key":"2026033012312262700_ref169","article-title":"Abstract meaning representation (AMR) annotation release 1.0 LDC2014T12","volume-title":"Web Download. Philadelphia: Linguistic Data Consortium","author":"Knight","year":"2014"},{"key":"2026033012312262700_ref170","first-page":"1152","volume-title":"MAWPS: A math word problem repository","author":"Koncel-Kedziorski","year":"2016"},{"key":"2026033012312262700_ref171","doi-asserted-by":"publisher","first-page":"2284","DOI":"10.18653\/v1\/N19-1238","volume-title":"Text Generation from Knowledge Graphs with Graph Transformers","author":"Koncel-Kedziorski","year":"2019"},{"key":"2026033012312262700_ref172","volume-title":"ImageNet Classification with Deep Convolutional Neural Networks","author":"Krizhevsky","year":"2012"},{"key":"2026033012312262700_ref173","first-page":"382","volume-title":"Difficulty-controllable multi-hop question generation from knowledge graphs","author":"Kumar","year":"2019"},{"key":"2026033012312262700_ref174","first-page":"282","volume-title":"Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data","author":"Lafferty","year":"2001"},{"key":"2026033012312262700_ref175","volume-title":"ALBERT: A Lite BERT for Self-supervised Learning of Language Representations","author":"Lan","year":"2019"},{"key":"2026033012312262700_ref176","first-page":"331","volume-title":"Newsweeder: Learning to filter netnews","author":"Lang","year":"1995"},{"key":"2026033012312262700_ref177","first-page":"2708","article-title":"A neural autoregressive topic model","volume":"25","author":"Larochelle","year":"2012","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2026033012312262700_ref178","first-page":"1188","volume-title":"Distributed representations of sentences and documents","author":"Le","year":"2014"},{"key":"2026033012312262700_ref179","doi-asserted-by":"crossref","DOI":"10.1145\/3387904.3389268","article-title":"Improved code summarization via a graph neural network","volume-title":"arXiv preprint","author":"LeClair","year":"2020"},{"key":"2026033012312262700_ref180","first-page":"255","volume-title":"Convolutional networks for images, speech, and time series","author":"LeCun","year":"1998"},{"key":"2026033012312262700_ref181","volume-title":"Mathematical Reasoning in Latent Space","author":"Lee","year":"2020"},{"key":"2026033012312262700_ref182","first-page":"28","volume-title":"Stanford\u2019s multi-pass sieve coreference resolution system at the conll-2011 shared task","author":"Lee","year":"2011"},{"key":"2026033012312262700_ref183","volume-title":"The winograd schema challenge","author":"Levesque","year":"2012"},{"key":"2026033012312262700_ref184","volume-title":"Finite geometrical systems: six public lectues delivered in February, 1940, at the University of Calcutta","author":"Levi","year":"1942"},{"issue":"Apr","key":"2026033012312262700_ref185","first-page":"361","article-title":"Rcv1: A new benchmark collection for text categorization research","volume":"5","author":"Lewis","year":"2004","journal-title":"Journal of machine learning research"},{"key":"2026033012312262700_ref186","doi-asserted-by":"publisher","first-page":"2594","DOI":"10.18653\/v1\/P19-1247","volume-title":"Encoding Social Information with Graph Convolutional Networks for Political Perspective Detection in News Media","author":"Li","year":"2019"},{"key":"2026033012312262700_ref187","first-page":"2723","volume-title":"Semi-supervised entity alignment via joint knowledge embedding model and cross-graph model","author":"Li","year":"2019"},{"key":"2026033012312262700_ref188","first-page":"599","volume-title":"Context-Aware Graph Segmentation for Graph-Based Translation","author":"Li","year":"2017"},{"key":"2026033012312262700_ref189","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v32i1.11691","volume-title":"Adaptive graph convolutional neural networks","author":"Li","year":"2018"},{"key":"2026033012312262700_ref190","doi-asserted-by":"publisher","first-page":"2841","DOI":"10.18653\/v1\/2020.findings-emnlp.255","volume-title":"Graph-to-Tree Neural Networks for Learning Structured Input-Output Translation with Applications to Semantic Parsing and Math Word Problem","author":"Li","year":"2020"},{"key":"2026033012312262700_ref191","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/2020.acl-main.555","article-title":"Leveraging Graph to Improve Abstractive Multi-Document Summarization","volume-title":"arXiv preprint","author":"Li","year":"2020"},{"key":"2026033012312262700_ref192","article-title":"Auto completion of user interface layout design using transformer-based tree decoders","volume-title":"arXiv preprint","author":"Li","year":"2020"},{"key":"2026033012312262700_ref193","first-page":"6116","volume-title":"Visual question generation as dual task of visual question answering","author":"Li","year":"2018"},{"key":"2026033012312262700_ref194","article-title":"Gated graph sequence neural networks","volume-title":"arXiv preprint","author":"Li","year":"2015"},{"key":"2026033012312262700_ref195","first-page":"2401","volume-title":"A unified syntax-aware framework for semantic role labeling","author":"Li","year":"2018"},{"key":"2026033012312262700_ref196","article-title":"Abstract meaning representation for multi-document summarization","volume-title":"arXiv preprint","author":"Liao","year":"2018"},{"key":"2026033012312262700_ref197","doi-asserted-by":"publisher","first-page":"2829","DOI":"10.18653\/v1\/D19-1282","volume-title":"KagNet: Knowledge-Aware Graph Networks for Commonsense Reasoning","author":"Lin","year":"2019"},{"key":"2026033012312262700_ref198","first-page":"2822","volume-title":"KagNet: Knowledge-Aware Graph Networks for Commonsense Reasoning","author":"Lin","year":"2019"},{"key":"2026033012312262700_ref199","first-page":"3243","volume-title":"Multi-Hop Knowledge Graph Reasoning with Reward Shaping","author":"Lin","year":"2018"},{"key":"2026033012312262700_ref200","doi-asserted-by":"publisher","first-page":"4821","DOI":"10.18653\/v1\/D19-1488","volume-title":"Heterogeneous Graph Attention Networks for Semi-supervised Short Text Classification","author":"Linmei","year":"2019"},{"key":"2026033012312262700_ref201","first-page":"6284","volume-title":"Matching Article Pairs with Graphical Decomposition and Convolutions","author":"Liu","year":"2019"},{"key":"2026033012312262700_ref202","first-page":"463","volume-title":"Graph Neural Networks in Natural Language Processing","author":"Liu","year":"2022"},{"key":"2026033012312262700_ref203","first-page":"1106","volume-title":"Learning to Generate Questions by LearningWhat Not to Generate","author":"Liu","year":"2019"},{"issue":"10","key":"2026033012312262700_ref204","doi-asserted-by":"crossref","first-page":"1103","DOI":"10.1021\/acscentsci.7b00303","article-title":"Retrosynthetic reaction prediction using neural sequence-to-sequence models","volume":"3","author":"Liu","year":"2017","journal-title":"ACS central science"},{"key":"2026033012312262700_ref205","first-page":"716","volume-title":"Semantic role features for machine translation","author":"Liu","year":"2010"},{"key":"2026033012312262700_ref206","doi-asserted-by":"publisher","first-page":"413","DOI":"10.1162\/tacl_a_00070","article-title":"In-Order Transition-based Constituent Parsing","volume":"5","author":"Liu","year":"2017","journal-title":"Transactions of the Association for Computational Linguistics"},{"key":"2026033012312262700_ref207","article-title":"DIG: A Turnkey Library for Diving into Graph Deep Learning Research","volume-title":"arXiv preprint","author":"Liu","year":"2021"},{"key":"2026033012312262700_ref208","first-page":"6762","volume-title":"Contextualized non-local neural networks for sequence learning","author":"Liu","year":"2019"},{"key":"2026033012312262700_ref209","first-page":"2873","volume-title":"Recurrent neural network for text classification with multi-task learning","author":"Liu","year":"2016"},{"key":"2026033012312262700_ref210","article-title":"Generating wikipedia by summarizing long sequences","volume-title":"arXiv preprint","author":"Liu","year":"2018"},{"key":"2026033012312262700_ref211","volume-title":"Retrieval-Augmented Generation for Code Summarization via Hybrid GNN","author":"Liu","year":"2021"},{"key":"2026033012312262700_ref212","doi-asserted-by":"publisher","first-page":"1247","DOI":"10.18653\/v1\/D18-1156","volume-title":"Jointly Multiple Events Extraction via Attention-based Graph Information Aggregation","author":"Liu","year":"2018"},{"key":"2026033012312262700_ref213","first-page":"8409","volume-title":"Tensor Graph Convolutional Networks for Text Classification","author":"Liu","year":"2020"},{"key":"2026033012312262700_ref214","first-page":"1952","volume-title":"Lcqmc: A large-scale chinese question matching corpus","author":"Liu","year":"2018"},{"key":"2026033012312262700_ref215","article-title":"Fine-tune BERT for extractive summarization","volume-title":"arXiv preprint","author":"Liu","year":"2019"},{"key":"2026033012312262700_ref216","article-title":"Roberta: A robustly optimized bert pretraining approach","volume-title":"arXiv preprint","author":"Liu","year":"2019"},{"key":"2026033012312262700_ref217","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v35i15.17585","volume-title":"A Graph Reasoning Network for Multi-turn Response Selection via Customized Pre-training","author":"Liu","year":"2021"},{"key":"2026033012312262700_ref218","doi-asserted-by":"publisher","first-page":"1065","DOI":"10.1145\/3394486.3403150","volume-title":"Graph Structural-topic Neural Network","author":"Long","year":"2020"},{"key":"2026033012312262700_ref219","first-page":"285","volume-title":"The Ubuntu Dialogue Corpus: A Large Dataset for Research in Unstructured Multi-Turn Dialogue Systems","author":"Lowe","year":"2015"},{"key":"2026033012312262700_ref220","first-page":"1367","article-title":"A deep architecture for matching short texts","volume":"26","author":"Lu","year":"2013","journal-title":"Advances in neural information processing systems"},{"key":"2026033012312262700_ref221","first-page":"3219","volume-title":"Multi-Task Identification of Entities, Relations, and Coreference for Scientific Knowledge Graph Construction","author":"Luan","year":"2018"},{"key":"2026033012312262700_ref222","first-page":"3036","volume-title":"A general framework for information extraction using dynamic span graphs","author":"Luan","year":"2019"},{"key":"2026033012312262700_ref223","first-page":"3","volume-title":"Ze lemoyer and Michael Collins. Learning to map sentences to logical form: Structured classification with probabilistic categorial grammars","author":"Luke","year":"2005"},{"key":"2026033012312262700_ref224","doi-asserted-by":"publisher","first-page":"6408","DOI":"10.18653\/v1\/2020.acl-main.571","volume-title":"Bipartite Flat-Graph Network for Nested Named Entity Recognition","author":"Luo","year":"2020"},{"key":"2026033012312262700_ref225","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/D15-1166","article-title":"Effective approaches to attention-based neural machine translation","volume-title":"arXiv preprint","author":"Luong","year":"2015"},{"key":"2026033012312262700_ref226","doi-asserted-by":"publisher","first-page":"1403","DOI":"10.18653\/v1\/P18-1130","volume-title":"Stack-Pointer Networks for Dependency Parsing","author":"Ma","year":"2018"},{"key":"2026033012312262700_ref227","first-page":"723","volume-title":"Graph convolutional networks with eigenpooling","author":"Ma","year":"2019"},{"key":"2026033012312262700_ref228","first-page":"2925","article-title":"Com-monsense Knowledge Base Completion with Structural and Semantic Context","volume-title":"AAAI","author":"Malaviya","year":"2020"},{"key":"2026033012312262700_ref229","volume-title":"Rhetorical structure theory: A theory of text organization","author":"Mann","year":"1987"},{"key":"2026033012312262700_ref230","doi-asserted-by":"publisher","first-page":"486","DOI":"10.18653\/v1\/N18-2078","volume-title":"Exploiting Semantics in Neural Machine Translation with Graph Convolutional Networks","author":"Marcheggiani","year":"2018"},{"key":"2026033012312262700_ref231","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/K17-1041","article-title":"A simple and accurate syntax-agnostic neural model for dependency-based semantic role labeling","volume-title":"arXiv preprint","author":"Marcheggiani","year":"2017"},{"key":"2026033012312262700_ref232","doi-asserted-by":"publisher","first-page":"1","DOI":"10.18653\/v1\/W18-6501","volume-title":"Deep Graph Convolutional Encoders for Structured Data to Text Generation","author":"Marcheggiani","year":"2018"},{"key":"2026033012312262700_ref233","first-page":"1506","volume-title":"Encoding Sentences with Graph Convolutional Networks for Semantic Role Labeling","author":"Marcheggiani","year":"2017"},{"key":"2026033012312262700_ref234","first-page":"3915","volume-title":"Graph Convolutions over Constituent Trees for Syntax-Aware Semantic Role Labeling","author":"Marcheggiani","year":"2020"},{"key":"2026033012312262700_ref235","first-page":"193","volume-title":"Semantic role labeling as sequential tagging","author":"Marquez","year":"2005"},{"key":"2026033012312262700_ref236","first-page":"1727","volume-title":"Neural variational inference for text processing","author":"Miao","year":"2016"},{"key":"2026033012312262700_ref237","first-page":"411","volume-title":"Unsupervised large-vocabulary word sense disambiguation with graph-based algorithms for sequence data labeling","author":"Mihalcea","year":"2005"},{"key":"2026033012312262700_ref238","doi-asserted-by":"crossref","DOI":"10.1017\/CBO9780511976247","volume-title":"Graph-based natural language processing and information retrieval","author":"Mihalcea","year":"2011"},{"key":"2026033012312262700_ref239","first-page":"404","volume-title":"Textrank: Bringing order into text","author":"Mihalcea","year":"2004"},{"key":"2026033012312262700_ref240","first-page":"2381","volume-title":"Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering","author":"Mihaylov","year":"2018"},{"key":"2026033012312262700_ref241","first-page":"3111","volume-title":"Distributed Representations of Words and Phrases and their Compositionality","author":"Mikolov","year":"2013"},{"key":"2026033012312262700_ref242","doi-asserted-by":"publisher","first-page":"1400","DOI":"10.18653\/v1\/D16-1147","volume-title":"Key-Value Memory Networks for Directly Reading Documents","author":"Miller","year":"2016"},{"key":"2026033012312262700_ref243","first-page":"27","volume-title":"Contextual search and name disambiguation in email using graphs","author":"Minkov","year":"2006"},{"key":"2026033012312262700_ref244","first-page":"520","volume-title":"Iterative translation disambiguation for cross-language information retrieval","author":"Monz","year":"2005"},{"key":"2026033012312262700_ref245","volume-title":"Rectified linear units improve restricted boltzmann machines","author":"Nair","year":"2010"},{"key":"2026033012312262700_ref246","first-page":"280","volume-title":"Abstractive Text Summarization using Sequence-to-sequence RNNs and Beyond","author":"Nallapati","year":"2016"},{"key":"2026033012312262700_ref247","doi-asserted-by":"publisher","first-page":"4710","DOI":"10.18653\/v1\/P19-1466","volume-title":"Learning Attention-based Embeddings for Relation Prediction in Knowledge Graphs","author":"Nathani","year":"2019"},{"key":"2026033012312262700_ref248","first-page":"4710","volume-title":"Learning Attention-based Embeddings for Relation Prediction in Knowledge Graphs","author":"Nathani","year":"2019"},{"key":"2026033012312262700_ref249","first-page":"5900","volume-title":"Graph convolutional networks with argument-aware pooling for event detection","author":"Nguyen","year":"2018"},{"key":"2026033012312262700_ref250","first-page":"395","volume-title":"Word sense disambiguation using label propagation based semi-supervised learning","author":"Niu","year":"2005"},{"key":"2026033012312262700_ref251","unstructured":"Nivre, J.\n            et al.\n           (2018). \u201cUniversal Dependencies 2.2\u201d. URL: http:\/\/hdl.handle.net\/11234\/1-2837."},{"key":"2026033012312262700_ref252","first-page":"8334","volume-title":"Learning Conditioned Graph Structures for Interpretable Visual Question Answering","author":"Norcliffe-Brown","year":"2018"},{"key":"2026033012312262700_ref253","volume-title":"Tech. rep.","author":"Page","year":"1999"},{"issue":"4","key":"2026033012312262700_ref254","doi-asserted-by":"crossref","first-page":"694","DOI":"10.1109\/TASLP.2016.2520371","article-title":"Deep sentence embedding using long short-term memory networks: Analysis and application to information retrieval","volume":"24","author":"Palangi","year":"2016","journal-title":"IEEE\/ACM Transactions on Audio, Speech, and Language Processing"},{"key":"2026033012312262700_ref255","first-page":"1463","volume-title":"Semantic Graphs for Generating Deep Questions","author":"Pan","year":"2020"},{"key":"2026033012312262700_ref256","first-page":"271","volume-title":"A Sentimental Education: Sentiment Analysis Using Subjectivity Summarization Based on Minimum Cuts","author":"Pang","year":"2004"},{"key":"2026033012312262700_ref257","volume-title":"Thumbs up? Sentiment Classification using Machine Learning Techniques","author":"Pang","year":"2002"},{"key":"2026033012312262700_ref258","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v30i1.10341","volume-title":"Text matching as image recognition","author":"Pang","year":"2016"},{"key":"2026033012312262700_ref259","volume-title":"A Deep Reinforced Model for Abstractive Summarization","author":"Paulus","year":"2018"},{"key":"2026033012312262700_ref260","first-page":"1063","volume-title":"Large-scale hierarchical text classification with recursively regularized deep graph-cnn","author":"Peng","year":"2018"},{"key":"2026033012312262700_ref261","volume-title":"Random Feature Attention","author":"Peng","year":"2021"},{"key":"2026033012312262700_ref262","first-page":"1532","volume-title":"Glove: Global vectors for word representation","author":"Pennington","year":"2014"},{"key":"2026033012312262700_ref263","first-page":"2227","volume-title":"Deep Contextualized Word Representations","author":"Peters","year":"2018"},{"key":"2026033012312262700_ref264","first-page":"91","volume-title":"Learning to classify short and sparse text & web with hidden topics from large-scale data collections","author":"Phan","year":"2008"},{"key":"2026033012312262700_ref265","first-page":"275","volume-title":"A language modeling approach to information retrieval","author":"Ponte","year":"1998"},{"key":"2026033012312262700_ref266","first-page":"19","volume-title":"Semeval-2016 task 5: Aspect based sentiment analysis","author":"Pontiki","year":"2016"},{"key":"2026033012312262700_ref267","first-page":"486","volume-title":"Semeval-2015 task 12: Aspect based sentiment analysis","author":"Pontiki","year":"2015"},{"key":"2026033012312262700_ref268","doi-asserted-by":"publisher","first-page":"27","DOI":"10.3115\/v1\/S14-2004","volume-title":"SemEval-2014 Task 4: Aspect Based Sentiment Analysis","author":"Pontiki","year":"2014"},{"key":"2026033012312262700_ref269","doi-asserted-by":"publisher","first-page":"4543","DOI":"10.18653\/v1\/2020.findings-emnlp.407","volume-title":"Improving Aspect-based Sentiment Analysis with Gated Graph Convolutional Networks and Syntax-based Regulation","author":"Pouran Ben Veyseh","year":"2020"},{"key":"2026033012312262700_ref270","doi-asserted-by":"publisher","first-page":"425","DOI":"10.3115\/v1\/D14-1048","volume-title":"Aligning English Strings with Abstract Meaning Representation Graphs","author":"Pourdamghani","year":"2014"},{"key":"2026033012312262700_ref271","first-page":"21","volume-title":"Generating english from abstract meaning representations","author":"Pourdamghani","year":"2016"},{"key":"2026033012312262700_ref272","first-page":"751","volume-title":"GraphIE: A Graph-Based Framework for Information Extraction","author":"Qian","year":"2019"},{"key":"2026033012312262700_ref273","first-page":"1150","volume-title":"Gcc: Graph contrastive coding for graph neural network pre-training","author":"Qiu","year":"2020"},{"key":"2026033012312262700_ref274","doi-asserted-by":"publisher","first-page":"6140","DOI":"10.18653\/v1\/P19-1617","volume-title":"Dynamically Fused Graph Network for Multi-hop Reasoning","author":"Qiu","year":"2019"},{"key":"2026033012312262700_ref275","first-page":"7867","volume-title":"Few-shot Relation Extraction via Bayesian Meta-learning on Relation Graphs","author":"Qu","year":"2020"},{"issue":"8","key":"2026033012312262700_ref276","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"key":"2026033012312262700_ref277","volume-title":"SQuAD: 100, 000+ Questions for Machine Comprehension of Text","author":"Rajpurkar","year":"2016"},{"key":"2026033012312262700_ref278","first-page":"23","volume-title":"Random walks for text semantic similarity","author":"Ramage","year":"2009"},{"key":"2026033012312262700_ref279","first-page":"2474","volume-title":"NumNet: Machine Reading Comprehension with Numerical Reasoning","author":"Ran","year":"2019"},{"key":"2026033012312262700_ref280","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/P18-1043","article-title":"Event2mind: Commonsense inference on events, intents, and reactions","volume-title":"arXiv preprint","author":"Rashkin","year":"2018"},{"key":"2026033012312262700_ref281","doi-asserted-by":"crossref","first-page":"249","DOI":"10.1162\/tacl_a_00266","article-title":"Coqa: A conversational question answering challenge","volume":"7","author":"Reddy","year":"2019","journal-title":"Transactions of the Association for Computational Linguistics"},{"key":"2026033012312262700_ref282","article-title":"Yolov3: An incremental improvement","volume-title":"arXiv preprint","author":"Redmon","year":"2018"},{"key":"2026033012312262700_ref283","doi-asserted-by":"publisher","first-page":"3183","DOI":"10.18653\/v1\/D19-1314","volume-title":"Enhancing AMR-to-Text Generation with Dual Graph Representations","author":"Ribeiro","year":"2019"},{"key":"2026033012312262700_ref284","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/D19-1314","article-title":"Enhancing amr-to-text generation with dual graph representations","volume-title":"arXiv preprint","author":"Ribeiro","year":"2019"},{"key":"2026033012312262700_ref285","first-page":"148","volume-title":"Modeling relations and their mentions without labeled text","author":"Riedel","year":"2010"},{"key":"2026033012312262700_ref286","article-title":"Stronger Transformers for Neural Multi-Hop Question Generation","volume-title":"arXiv preprint","author":"Sachan","year":"2020"},{"key":"2026033012312262700_ref287","first-page":"125","volume-title":"A Classifier-Based Parser with Linear Run-Time Complexity","author":"Sagae","year":"2005"},{"key":"2026033012312262700_ref288","doi-asserted-by":"publisher","first-page":"4309","DOI":"10.18653\/v1\/P19-1423","volume-title":"Inter-sentence Relation Extraction with Document-level Graph Convolutional Neural Network","author":"Sahu","year":"2019"},{"key":"2026033012312262700_ref289","volume-title":"The New York Times Annotated Corpus","author":"Sandhaus","year":"2008"},{"key":"2026033012312262700_ref290","first-page":"4974","volume-title":"A simple neural network module for relational reasoning","author":"Santoro","year":"2017"},{"key":"2026033012312262700_ref291","doi-asserted-by":"publisher","first-page":"4498","DOI":"10.18653\/v1\/2020.acl-main.412","volume-title":"Improving Multi-hop Question Answering over Knowledge Graphs using Knowledge Base Embeddings","author":"Saxena","year":"2020"},{"key":"2026033012312262700_ref292","first-page":"593607","volume-title":"Modeling relational data with graph convolutional networks","author":"Schlichtkrull","year":"2018"},{"issue":"11","key":"2026033012312262700_ref293","doi-asserted-by":"publisher","first-page":"2673","DOI":"10.1109\/78.650093","article-title":"Bidirectional recurrent neural networks","volume":"45","author":"Schuster","year":"1997","journal-title":"IEEE Transactions on Signal Processing"},{"key":"2026033012312262700_ref294","first-page":"1073","volume-title":"Get To The Point: Summarization with Pointer-Generator Networks","author":"See","year":"2017"},{"key":"2026033012312262700_ref295","volume-title":"Bidirectional Attention Flow for Machine Comprehension","author":"Seo","year":"2017"},{"key":"2026033012312262700_ref296","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v30i1.9883","volume-title":"Building end-to-end dialogue systems using generative hierarchical neural network models","author":"Serban","year":"2016"},{"key":"2026033012312262700_ref297","volume-title":"A hierarchical latent variable encoderdecoder model for generating dialogues","author":"Serban","year":"2017"},{"key":"2026033012312262700_ref298","first-page":"3060","volume-title":"End-to-end structure-aware convolutional networks for knowledge base completion","author":"Shang","year":"2019"},{"issue":"05","key":"2026033012312262700_ref299","doi-asserted-by":"publisher","first-page":"8807","DOI":"10.1609\/aaai.v34i05.6408","article-title":"Graph-Based Transformer with Cross-Candidate Verification for Semantic Parsing","volume":"34","author":"Shao","year":"2020","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"2026033012312262700_ref300","doi-asserted-by":"publisher","first-page":"464","DOI":"10.18653\/v1\/N18-2074","volume-title":"Self-Attention with Relative Position Representations","author":"Shaw","year":"2018"},{"key":"2026033012312262700_ref301","first-page":"12","volume-title":"Using semantic roles to improve question answering","author":"Shen","year":"2007"},{"key":"2026033012312262700_ref302","first-page":"3531","volume-title":"Efficient attention: Attention with linear complexities","author":"Shen","year":"2021"},{"key":"2026033012312262700_ref303","first-page":"8818","volume-title":"A graph to graphs framework for retrosynthesis prediction","author":"Shi","year":"2020"},{"key":"2026033012312262700_ref304","first-page":"3693","volume-title":"Dynamic edge-conditioned filters in convolutional neural networks on graphs","author":"Simonovsky","year":"2017"},{"key":"2026033012312262700_ref305","doi-asserted-by":"crossref","first-page":"19","DOI":"10.1162\/tacl_a_00252","article-title":"Semantic neural machine translation using AMR","volume":"7","author":"Song","year":"2019","journal-title":"Transactions of the Association for Computational Linguistics"},{"key":"2026033012312262700_ref306","first-page":"7","volume-title":"AMR-to-text Generation with Synchronous Node Replacement Grammar","author":"Song","year":"2017"},{"key":"2026033012312262700_ref307","doi-asserted-by":"publisher","first-page":"7987","DOI":"10.18653\/v1\/2020.acl-main.712","volume-title":"Structural Information Preserving for Graph-to-Text Generation","author":"Song","year":"2020"},{"key":"2026033012312262700_ref308","first-page":"569","volume-title":"Leveraging context information for natural question generation","author":"Song","year":"2018"},{"key":"2026033012312262700_ref309","article-title":"Exploring graph-structured passage representation for multi-hop reading comprehension with graph neural networks","volume-title":"arXiv preprint","author":"Song","year":"2018"},{"key":"2026033012312262700_ref310","doi-asserted-by":"publisher","first-page":"1616","DOI":"10.18653\/v1\/P18-1150","volume-title":"A Graph-to-Sequence Model for AMR-to-Text Generation","author":"Song","year":"2018"},{"key":"2026033012312262700_ref311","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/P18-1150","article-title":"A graph-to-sequence model for amr-to-text generation","volume-title":"arXiv preprint","author":"Song","year":"2018"},{"key":"2026033012312262700_ref312","doi-asserted-by":"publisher","first-page":"2226","DOI":"10.18653\/v1\/D18-1246","volume-title":"N-ary Relation Extraction using Graph-State LSTM","author":"Song","year":"2018"},{"key":"2026033012312262700_ref313","first-page":"3306","volume-title":"Modeling Semantics with Gated Graph Neural Networks for Knowledge Base Question Answering","author":"Sorokin","year":"2018"},{"key":"2026033012312262700_ref314","article-title":"Modeling semantics with gated graph neural networks for knowledge base question answering","volume-title":"arXiv preprint","author":"Sorokin","year":"2018"},{"key":"2026033012312262700_ref315","volume-title":"Conceptnet 5.5: An open multilingual graph of general knowledge","author":"Speer","year":"2017"},{"key":"2026033012312262700_ref316","doi-asserted-by":"publisher","first-page":"4636","DOI":"10.18653\/v1\/2020.findings-emnlp.416","volume-title":"Multi-hop Question Generation with Graph Convolutional Network","author":"Su","year":"2020"},{"issue":"3","key":"2026033012312262700_ref317","doi-asserted-by":"crossref","first-page":"203","DOI":"10.1016\/j.websem.2008.06.001","article-title":"Yago: A large ontology from wikipedia and wordnet","volume":"6","author":"Suchanek","year":"2008","journal-title":"Journal of Web Semantics"},{"key":"2026033012312262700_ref318","first-page":"3821","volume-title":"Leverage lexical knowledge for chinese named entity recognition via collaborative graph network","author":"Sui","year":"2019"},{"key":"2026033012312262700_ref319","first-page":"2440","volume-title":"End-to-end memory networks","author":"Sukhbaatar","year":"2015"},{"key":"2026033012312262700_ref320","doi-asserted-by":"publisher","first-page":"1361","DOI":"10.18653\/v1\/P19-1131","volume-title":"Joint Type Inference on Entities and Relations via Graph Convolutional Networks","author":"Sun","year":"2019"},{"key":"2026033012312262700_ref321","doi-asserted-by":"publisher","first-page":"2380","DOI":"10.18653\/v1\/D19-1242","volume-title":"PullNet: Open Domain Question Answering with Iterative Retrieval on Knowledge Bases and Text","author":"Sun","year":"2019"},{"key":"2026033012312262700_ref322","doi-asserted-by":"publisher","first-page":"4231","DOI":"10.18653\/v1\/D18-1455","volume-title":"Open Domain Question Answering Using Early Fusion of Knowledge Bases and Text","author":"Sun","year":"2018"},{"key":"2026033012312262700_ref323","doi-asserted-by":"publisher","first-page":"5679","DOI":"10.18653\/v1\/D19-1569","volume-title":"Aspect-Level Sentiment Analysis Via Convolution over Dependency Tree","author":"Sun","year":"2019"},{"key":"2026033012312262700_ref324","first-page":"3660","volume-title":"CoLAKE: Contextualized Language and Knowledge Embedding","author":"Sun","year":"2020"},{"issue":"11","key":"2026033012312262700_ref325","doi-asserted-by":"crossref","first-page":"992","DOI":"10.14778\/3402707.3402736","article-title":"Pathsim: Meta path-based top-k similarity search in heterogeneous information networks","volume":"4","author":"Sun","year":"2011","journal-title":"Proceedings of the VLDB Endowment"},{"key":"2026033012312262700_ref326","first-page":"628","volume-title":"Cross-lingual entity alignment via joint attribute-preserving embedding","author":"Sun","year":"2017"},{"key":"2026033012312262700_ref327","first-page":"4396","article-title":"Bootstrapping Entity Alignment with Knowledge Graph Embedding","volume":"18","author":"Sun","year":"2018","journal-title":"IJCAI"},{"key":"2026033012312262700_ref328","first-page":"222","volume-title":"Knowledge graph alignment network with gated multi-hop neighborhood aggregation","author":"Sun","year":"2020"},{"key":"2026033012312262700_ref329","first-page":"8984","volume-title":"Treegen: A tree-based transformer architecture for code generation","author":"Sun","year":"2020"},{"key":"2026033012312262700_ref330","first-page":"3104","volume-title":"Sequence to Sequence Learning with Neural Networks","author":"Sutskever","year":"2014"},{"key":"2026033012312262700_ref331","first-page":"1556","volume-title":"Improved Semantic Representations From Tree-Structured Long Short-Term Memory Networks","author":"Tai","year":"2015"},{"key":"2026033012312262700_ref332","first-page":"641","volume-title":"The Web as a Knowledge-Base for Answering Complex Questions","author":"Talmor","year":"2018"},{"key":"2026033012312262700_ref333","volume-title":"CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge","author":"Talmor","year":"2019"},{"key":"2026033012312262700_ref334","first-page":"3298","volume-title":"Effective LSTMs for Target-Dependent Sentiment Classification","author":"Tang","year":"2016"},{"key":"2026033012312262700_ref335","doi-asserted-by":"publisher","first-page":"6578","DOI":"10.18653\/v1\/2020.acl-main.588","volume-title":"Dependency Graph Enhanced Dual-transformer Structure for Aspect-based Sentiment Classification","author":"Tang","year":"2020"},{"key":"2026033012312262700_ref336","first-page":"1165","volume-title":"Pte: Predictive text embedding through large-scale heterogeneous text networks","author":"Tang","year":"2015"},{"key":"2026033012312262700_ref337","first-page":"3905","volume-title":"Multi-hop Reading Comprehension across Documents with Path-based Graph Convolutional Network","author":"Tang","year":"2020"},{"key":"2026033012312262700_ref338","doi-asserted-by":"crossref","DOI":"10.24963\/ijcai.2020\/540","article-title":"Multi-hop reading comprehension across documents with path-based graph convolutional network","volume-title":"arXiv preprint","author":"Tang","year":"2020"},{"key":"2026033012312262700_ref339","first-page":"782","volume-title":"Semantic document engineering with WordNet and PageRank","author":"Tarau","year":"2005"},{"key":"2026033012312262700_ref340","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1007\/978-94-010-0201-1_1","article-title":"The Penn treebank: an overview","volume-title":"Treebanks","author":"Taylor","year":"2003"},{"key":"2026033012312262700_ref341","first-page":"9448","volume-title":"Inductive relation prediction by subgraph reasoning","author":"Teru","year":"2020"},{"key":"2026033012312262700_ref342","doi-asserted-by":"publisher","first-page":"42","DOI":"10.18653\/v1\/D19-5306","volume-title":"Identifying Supporting Facts for Multi-hop Question Answering with Document Graph Networks","author":"Thayaparan","year":"2019"},{"key":"2026033012312262700_ref343","volume-title":"All the news: 143,000 articles from 15 american publications","author":"Thompson","year":"2017"},{"key":"2026033012312262700_ref344","first-page":"1499","volume-title":"Representing text for joint embedding of text and knowledge bases","author":"Toutanova","year":"2015"},{"key":"2026033012312262700_ref345","first-page":"191","volume-title":"NewsQA: A Machine Comprehension Dataset","author":"Trischler","year":"2017"},{"key":"2026033012312262700_ref346","first-page":"2071","volume-title":"Complex embeddings for simple link prediction","author":"Trouillon","year":"2016"},{"key":"2026033012312262700_ref347","first-page":"4335","volume-title":"Transformer Dissection: An Unified Understanding for Transformer\u2019s Attention via the Lens of Kernel","author":"Tsai","year":"2019"},{"key":"2026033012312262700_ref348","doi-asserted-by":"publisher","first-page":"2704","DOI":"10.18653\/v1\/P19-1260","volume-title":"Multi-hop Reading Comprehension across Multiple Documents by Reasoning over Heterogeneous Graphs","author":"Tu","year":"2019"},{"key":"2026033012312262700_ref349","first-page":"2704","volume-title":"Multi-hop Reading Comprehension across Multiple Documents by Reasoning over Heterogeneous Graphs","author":"Tu","year":"2019"},{"key":"2026033012312262700_ref350","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/P16-1008","article-title":"Modeling coverage for neural machine translation","volume-title":"arXiv preprint","author":"Tu","year":"2016"},{"key":"2026033012312262700_ref351","first-page":"59","volume-title":"7th open challenge on question answering over linked data (QALD-7)","author":"Usbeck","year":"2017"},{"key":"2026033012312262700_ref352","doi-asserted-by":"publisher","first-page":"1257","DOI":"10.18653\/v1\/D18-1157","volume-title":"RESIDE: Improving Distantly-Supervised Neural Relation Extraction using Side Information","author":"Vashishth","year":"2018"},{"key":"2026033012312262700_ref353","article-title":"Composition-based multi-relational graph convolutional networks","volume-title":"arXiv preprint","author":"Vashishth","year":"2019"},{"key":"2026033012312262700_ref354","volume-title":"Attention is All you Need","author":"Vaswani","year":"2017"},{"key":"2026033012312262700_ref355","volume-title":"Pointer Graph Networks","author":"Velickovic","year":"2020"},{"key":"2026033012312262700_ref356","volume-title":"Graph Attention Networks","author":"Velickovic","year":"2018"},{"key":"2026033012312262700_ref357","volume-title":"Order Matters: Sequence to sequence for sets","author":"Vinyals","year":"2016"},{"key":"2026033012312262700_ref358","first-page":"2692","volume-title":"Pointer networks","author":"Vinyals","year":"2015"},{"key":"2026033012312262700_ref359","first-page":"376","volume-title":"Classification of short texts by deploying topical annotations","author":"Vitale","year":"2012"},{"key":"2026033012312262700_ref360","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v30i1.10342","volume-title":"A deep architecture for semantic matching with multiple positional sentence representations","author":"Wan","year":"2016"},{"key":"2026033012312262700_ref361","doi-asserted-by":"publisher","first-page":"6209","DOI":"10.18653\/v1\/2020.acl-main.553","volume-title":"Heterogeneous Graph Neural Networks for Extractive Document Summarization","author":"Wang","year":"2020"},{"key":"2026033012312262700_ref362","doi-asserted-by":"publisher","first-page":"2623","DOI":"10.18653\/v1\/D19-1264","volume-title":"Incorporating Graph Attention Mechanism into Knowledge Graph Reasoning Based on Deep Reinforcement Learning","author":"Wang","year":"2019"},{"key":"2026033012312262700_ref363","doi-asserted-by":"publisher","first-page":"3229","DOI":"10.18653\/v1\/2020.acl-main.295","volume-title":"Relational Graph Attention Network for Aspect-based Sentiment Analysis","author":"Wang","year":"2020"},{"key":"2026033012312262700_ref364","doi-asserted-by":"publisher","first-page":"5159","DOI":"10.18653\/v1\/2020.coling-main.452","volume-title":"Answer-driven Deep Question Generation based on Reinforcement Learning","author":"Wang","year":"2020"},{"key":"2026033012312262700_ref365","first-page":"5159","volume-title":"Answer-driven Deep Question Generation based on Reinforcement Learning","author":"Wang","year":"2020"},{"key":"2026033012312262700_ref366","volume-title":"Deep Graph Library: Towards Efficient and Scalable Deep Learning on Graphs","author":"Wang","year":"2019"},{"key":"2026033012312262700_ref367","first-page":"7152","volume-title":"Logic attention based neighborhood aggregation for inductive knowledge graph embedding","author":"Wang","year":"2019"},{"issue":"6","key":"2026033012312262700_ref368","doi-asserted-by":"crossref","first-page":"102098","DOI":"10.1016\/j.ipm.2019.102098","article-title":"Atm: Adversarial-neural topic model","volume":"56","author":"Wang","year":"2019","journal-title":"Information Processing & Management"},{"key":"2026033012312262700_ref369","article-title":"Linformer: Self-Attention with Linear Complexity","volume":"abs\/2006.04768","author":"Wang","year":"2020","journal-title":"CoRR"},{"key":"2026033012312262700_ref370","doi-asserted-by":"crossref","first-page":"19","DOI":"10.1162\/tacl_a_00297","article-title":"AMR-To-Text Generation with Graph Transformer","volume":"8","author":"Wang","year":"2020","journal-title":"Transactions of the Association for Computational Linguistics"},{"key":"2026033012312262700_ref371","doi-asserted-by":"publisher","first-page":"3919","DOI":"10.24963\/ijcai.2020\/542","volume-title":"Better AMR-To-Text Generation with Graph Structure Reconstruction","author":"Wang","year":"2020"},{"key":"2026033012312262700_ref372","first-page":"2022","volume-title":"Heterogeneous graph attention network","author":"Wang","year":"2019"},{"issue":"01","key":"2026033012312262700_ref373","doi-asserted-by":"publisher","first-page":"7208","DOI":"10.1609\/aaai.v33i01.33017208","article-title":"Improving Natural Language Inference Using External Knowledge in the Science Questions Domain","volume":"33","author":"Wang","year":"2019","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"2026033012312262700_ref374","first-page":"845","volume-title":"Deep neural solver for math word problems","author":"Wang","year":"2017"},{"key":"2026033012312262700_ref375","first-page":"349","volume-title":"Cross-lingual knowledge graph alignment via graph convolutional networks","author":"Wang","year":"2018"},{"key":"2026033012312262700_ref376","doi-asserted-by":"publisher","first-page":"1672","DOI":"10.18653\/v1\/2020.emnlp-main.130","volume-title":"Knowledge Graph Alignment with Entity-Pair Embedding","author":"Wang","year":"2020"},{"key":"2026033012312262700_ref377","first-page":"5240","article-title":"Robust Embedding with Multi-Level Structures for Link Prediction","volume-title":"IJCAI","author":"Wang","year":"2019"},{"key":"2026033012312262700_ref378","doi-asserted-by":"crossref","first-page":"287","DOI":"10.1162\/tacl_a_00021","article-title":"Constructing datasets for multi-hop reading comprehension across documents","volume":"6","author":"Welbl","year":"2018","journal-title":"Transactions of the Association for Computational Linguistics"},{"key":"2026033012312262700_ref379","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/n18-1101.","volume-title":"A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference","author":"Williams","year":"2018"},{"issue":"4","key":"2026033012312262700_ref380","doi-asserted-by":"crossref","first-page":"121","DOI":"10.1609\/aimag.v35i4.2558","article-title":"The dialog state tracking challenge series","volume":"35","author":"Williams","year":"2014","journal-title":"AI Magazine"},{"issue":"3-4","key":"2026033012312262700_ref381","doi-asserted-by":"crossref","first-page":"229","DOI":"10.1023\/A:1022672621406","article-title":"Simple statistical gradient-following algorithms for connectionist reinforcement learning","volume":"8","author":"Williams","year":"1992","journal-title":"Machine learning"},{"key":"2026033012312262700_ref382","doi-asserted-by":"publisher","first-page":"5730","DOI":"10.18653\/v1\/2020.emnlp-main.462","volume-title":"TeMP: Temporal Message Passing for Temporal Knowledge Graph Completion","author":"Wu","year":"2020"},{"key":"2026033012312262700_ref383","doi-asserted-by":"crossref","first-page":"725","DOI":"10.1007\/978-981-16-6054-2","volume-title":"Graph Neural Networks: Foundations, Frontiers, and Applications","author":"Wu","year":"2022"},{"key":"2026033012312262700_ref384","doi-asserted-by":"publisher","first-page":"7137","DOI":"10.18653\/v1\/2020.emnlp-main.579","volume-title":"A Knowledge-Aware Sequence-to-Tree Network for Math Word Problem Solving","author":"Wu","year":"2020"},{"key":"2026033012312262700_ref385","first-page":"5278","volume-title":"Relation-aware entity alignment for heterogeneous knowledge graphs","author":"Wu","year":"2019"},{"key":"2026033012312262700_ref386","first-page":"240","volume-title":"Jointly Learning Entity and Relation Representations for Entity Alignment","author":"Wu","year":"2019"},{"key":"2026033012312262700_ref387","article-title":"Extracting Summary Knowledge Graphs from Long Documents","volume-title":"arXiv preprint","author":"Wu","year":"2020"},{"issue":"01","key":"2026033012312262700_ref388","doi-asserted-by":"publisher","first-page":"7297","DOI":"10.1609\/aaai.v33i01.33017297","article-title":"Graph Based Translation Memory for Neural Machine Translation","volume":"33","author":"Xia","year":"2019","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"2026033012312262700_ref389","first-page":"2979","volume-title":"Semantic Role Labeling with Heterogeneous Syntactic Knowledge","author":"Xia","year":"2020"},{"key":"2026033012312262700_ref390","doi-asserted-by":"publisher","first-page":"3090","DOI":"10.18653\/v1\/P19-1298","volume-title":"Lattice-Based Transformer Encoder for Neural Machine Translation","author":"Xiao","year":"2019"},{"key":"2026033012312262700_ref391","first-page":"5929","volume-title":"ReInceptionE: Relation-aware inception network with joint local-global structural information for knowledge graph embedding","author":"Xie","year":"2020"},{"key":"2026033012312262700_ref392","volume-title":"Dynamic Coattention Networks For Question Answering","author":"Xiong","year":"2017"},{"key":"2026033012312262700_ref393","first-page":"564","volume-title":"DeepPath: A Reinforcement Learning Method for Knowledge Graph Reasoning","author":"Xiong","year":"2017"},{"key":"2026033012312262700_ref394","first-page":"5021","volume-title":"Discourse-aware neural extractive text summarization","author":"Xu","year":"2020"},{"key":"2026033012312262700_ref395","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v34i05.6476","article-title":"Coordinated Reasoning for Cross-Lingual Knowledge Graph Alignment","volume-title":"arXiv preprint","author":"Xu","year":"2020"},{"key":"2026033012312262700_ref396","doi-asserted-by":"publisher","first-page":"3156","DOI":"10.18653\/v1\/P19-1304","volume-title":"Cross-lingual Knowledge Graph Alignment via Graph Matching Neural Network","author":"Xu","year":"2019"},{"key":"2026033012312262700_ref397","doi-asserted-by":"publisher","first-page":"931","DOI":"10.18653\/v1\/D18-1112","volume-title":"SQL-to-Text Generation with Graph-to-Sequence Model","author":"Xu","year":"2018"},{"key":"2026033012312262700_ref398","article-title":"Graph2seq: Graph to sequence learning with attention-based neural networks","volume-title":"arXiv preprint","author":"Xu","year":"2018"},{"key":"2026033012312262700_ref399","doi-asserted-by":"publisher","first-page":"918","DOI":"10.18653\/v1\/D18-1110","volume-title":"Exploiting Rich Syntactic Information for Semantic Parsing with Graph-to-Sequence Model","author":"Xu","year":"2018"},{"key":"2026033012312262700_ref400","article-title":"Document Graph for Neural Machine Translation","volume":"abs\/2012.03477","author":"Xu","year":"2020","journal-title":"ArXiv"},{"key":"2026033012312262700_ref401","article-title":"Dynamically Pruned Message Passing Networks for Large-Scale Knowledge Graph Reasoning","volume-title":"arXiv preprint","author":"Xu","year":"2019"},{"key":"2026033012312262700_ref402","doi-asserted-by":"publisher","first-page":"5766","DOI":"10.18653\/v1\/D19-1582","volume-title":"Event Detection with Multi-Order Graph Convolution and Aggregated Attention","author":"Yan","year":"2019"},{"key":"2026033012312262700_ref403","article-title":"Embedding entities and relations for learning and inference in knowledge bases","volume-title":"arXiv preprint","author":"Yang","year":"2014"},{"key":"2026033012312262700_ref404","first-page":"4422","volume-title":"Aligning Cross-Lingual Entities with Multi-Aspect Information","author":"Yang","year":"2019"},{"key":"2026033012312262700_ref405","article-title":"Strongly Incremental Constituency Parsing with Graph Neural Networks","volume-title":"arXiv preprint","author":"Yang","year":"2020"},{"key":"2026033012312262700_ref406","doi-asserted-by":"publisher","first-page":"144","DOI":"10.1145\/3366423.3380102","volume-title":"Graph Attention Topic Modeling Network","author":"Yang","year":"2020"},{"key":"2026033012312262700_ref407","first-page":"287","volume-title":"aNMM: Ranking short answer texts with attention-based neural matching model","author":"Yang","year":"2016"},{"key":"2026033012312262700_ref408","first-page":"2369","volume-title":"HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering","author":"Yang","year":"2018"},{"key":"2026033012312262700_ref409","first-page":"8950","volume-title":"Glomo: Unsupervised learning of transferable relational graphs","author":"Yang","year":"2018"},{"key":"2026033012312262700_ref410","first-page":"7370","volume-title":"Graph Convolutional Networks for Text Classification","author":"Yao","year":"2019"},{"key":"2026033012312262700_ref411","first-page":"7370","volume-title":"Graph convolutional networks for text classification","author":"Yao","year":"2019"},{"key":"2026033012312262700_ref412","first-page":"7145","volume-title":"Heterogeneous graph transformer for graph-to-sequence learning","author":"Yao","year":"2020"},{"key":"2026033012312262700_ref413","first-page":"684","volume-title":"Exploring visual relationship for image captioning","author":"Yao","year":"2018"},{"key":"2026033012312262700_ref414","volume-title":"QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answering","author":"Yasunaga","year":"2021"},{"key":"2026033012312262700_ref415","doi-asserted-by":"publisher","first-page":"452","DOI":"10.18653\/v1\/K17-1045","volume-title":"Graph-based Neural Multi-Document Summarization","author":"Yasunaga","year":"2017"},{"key":"2026033012312262700_ref416","first-page":"4135","article-title":"A Vectorized Relational Graph Convolutional Network for Multi-Relational Network Alignment","volume-title":"IJCAI","author":"Ye","year":"2019"},{"key":"2026033012312262700_ref417","first-page":"1321","volume-title":"Semantic Parsing via Staged Query Graph Generation: Question Answering with Knowledge Base","author":"Yih","year":"2015"},{"key":"2026033012312262700_ref418","first-page":"201","volume-title":"The value of semantic parse labeling for knowledge base question answering","author":"Yih","year":"2016"},{"key":"2026033012312262700_ref419","article-title":"Learning to represent edits","volume-title":"arXiv preprint","author":"Yin","year":"2018"},{"key":"2026033012312262700_ref420","doi-asserted-by":"publisher","first-page":"3025","DOI":"10.18653\/v1\/2020.acl-main.273","volume-title":"A Novel Graph-based Multi-modal Fusion Encoder for Neural Machine Translation","author":"Yin","year":"2020"},{"key":"2026033012312262700_ref421","article-title":"Hierarchical graph representation learning with differentiable pooling","volume-title":"arXiv preprint","author":"Ying","year":"2018"},{"key":"2026033012312262700_ref422","doi-asserted-by":"publisher","first-page":"3911","DOI":"10.18653\/v1\/D18-1425","volume-title":"Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Task","author":"Yu","year":"2018"},{"key":"2026033012312262700_ref423","first-page":"11983","article-title":"Graph Transformer Networks","volume":"32","author":"Yun","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2026033012312262700_ref424","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/D18-1009","article-title":"Swag: A large-scale adversarial dataset for grounded commonsense inference","volume-title":"arXiv preprint","author":"Zellers","year":"2018"},{"key":"2026033012312262700_ref425","doi-asserted-by":"publisher","first-page":"1630","DOI":"10.18653\/v1\/2020.emnlp-main.127","volume-title":"Double Graph Based Reasoning for Document-level Relation Extraction","author":"Zeng","year":"2020"},{"key":"2026033012312262700_ref426","first-page":"3249","volume-title":"Syntax-aware opinion role labeling with dependency graph convolutional networks","author":"Zhang","year":"2020"},{"key":"2026033012312262700_ref427","doi-asserted-by":"publisher","first-page":"4568","DOI":"10.18653\/v1\/D19-1464","volume-title":"Aspect-based Sentiment Classification with Aspect-specific Graph Convolutional Networks","author":"Zhang","year":"2019"},{"key":"2026033012312262700_ref428","first-page":"793","volume-title":"Heterogeneous graph neural network","author":"Zhang","year":"2019"},{"key":"2026033012312262700_ref429","doi-asserted-by":"crossref","DOI":"10.1145\/3292500.3330961","volume-title":"Heterogeneous Graph Neural Network","author":"Zhang","year":"2019"},{"key":"2026033012312262700_ref430","doi-asserted-by":"publisher","first-page":"3928","DOI":"10.18653\/v1\/2020.acl-main.362","volume-title":"Graph-to-Tree Learning for Solving Math Word Problems","author":"Zhang","year":"2020"},{"key":"2026033012312262700_ref431","doi-asserted-by":"publisher","first-page":"3540","DOI":"10.18653\/v1\/2020.emnlp-main.286","volume-title":"Convolution over Hierarchical Syntactic and Lexical Graphs for Aspect Level Sentiment Analysis","author":"Zhang","year":"2020"},{"key":"2026033012312262700_ref432","doi-asserted-by":"publisher","first-page":"15","DOI":"10.18653\/v1\/2020.findings-emnlp.2","volume-title":"Summarizing Chinese Medical Answer with Graph Convolution Networks and Question-focused Dual Attention","author":"Zhang","year":"2020"},{"key":"2026033012312262700_ref433","doi-asserted-by":"publisher","first-page":"3016","DOI":"10.18653\/v1\/N19-1306","volume-title":"Long-tail Relation Extraction via Knowledge Graph Em-beddings and Graph Convolution Networks","author":"Zhang","year":"2019"},{"key":"2026033012312262700_ref434","article-title":"Record: Bridging the gap between human and machine common-sense reading comprehension","volume-title":"arXiv preprint","author":"Zhang","year":"2018"},{"key":"2026033012312262700_ref435","first-page":"80","volume-title":"AMR Parsing as Sequence-to-Graph Transduction","author":"Zhang","year":"2019"},{"key":"2026033012312262700_ref436","doi-asserted-by":"publisher","first-page":"80","DOI":"10.18653\/v1\/P19-1009","volume-title":"AMR Parsing as Sequence-to-Graph Transduction","author":"Zhang","year":"2019"},{"key":"2026033012312262700_ref437","article-title":"Character-level convolutional networks for text classification","volume-title":"arXiv preprint","author":"Zhang","year":"2015"},{"key":"2026033012312262700_ref438","doi-asserted-by":"publisher","first-page":"2162","DOI":"10.18653\/v1\/2020.emnlp-main.169","volume-title":"Lightweight, Dynamic Graph Convolutional Networks for AMR-to-Text Generation","author":"Zhang","year":"2020"},{"key":"2026033012312262700_ref439","first-page":"4845","volume-title":"Very deep convolutional networks for end-to-end speech recognition","author":"Zhang","year":"2017"},{"key":"2026033012312262700_ref440","first-page":"317","volume-title":"Sentence-State LSTM for Text Representation","author":"Zhang","year":"2018"},{"key":"2026033012312262700_ref441","first-page":"334339","volume-title":"Every Document Owns Its Structure: Inductive Text Classification via Graph Neural Networks","author":"Zhang","year":"2020"},{"key":"2026033012312262700_ref442","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/2020.acl-main.31","article-title":"Every document owns its structure: Inductive text classification via graph neural networks","volume-title":"arXiv preprint","author":"Zhang","year":"2020"},{"key":"2026033012312262700_ref443","doi-asserted-by":"publisher","first-page":"2205","DOI":"10.18653\/v1\/D18-1244","volume-title":"Graph Convolution over Pruned Dependency Trees Improves Relation Extraction","author":"Zhang","year":"2018"},{"key":"2026033012312262700_ref444","first-page":"35","volume-title":"Position-aware attention and supervised data improve slot filling","author":"Zhang","year":"2017"},{"key":"2026033012312262700_ref445","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v32i1.12057","volume-title":"Variational reasoning for question answering with knowledge graph","author":"Zhang","year":"2018"},{"key":"2026033012312262700_ref446","first-page":"9612","article-title":"Relational Graph Neural Network with Hierarchical Attention for Knowledge Graph Completion","volume-title":"AAAI","author":"Zhang","year":"2020"},{"key":"2026033012312262700_ref447","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v35i5.16600","volume-title":"Heterogeneous Graph Structure Learning for Graph Neural Networks","author":"Zhao","year":"2021"},{"key":"2026033012312262700_ref448","first-page":"437","volume-title":"Improving Abstractive Dialogue Summarization with Graph Structures and Topic Words","author":"Zhao","year":"2020"},{"key":"2026033012312262700_ref449","doi-asserted-by":"publisher","first-page":"732","DOI":"10.18653\/v1\/2020.acl-main.67","volume-title":"Line Graph Enhanced AMR-to-Text Generation with Mix-Order Graph Attention Networks","author":"Zhao","year":"2020"},{"key":"2026033012312262700_ref450","first-page":"4495","volume-title":"Knowledge Graph Enhanced Neural Machine Translation via Multitask Learning on Sub-entity Granularity","author":"Zhao","year":"2020"},{"key":"2026033012312262700_ref451","first-page":"6708","volume-title":"Document Modeling with Graph Attention Networks for Multi-grained Machine Reading Comprehension","author":"Zheng","year":"2020"},{"key":"2026033012312262700_ref452","first-page":"8881","volume-title":"SRLGRN: Semantic Role Labeling Graph Reasoning Network","author":"Zheng","year":"2020"},{"key":"2026033012312262700_ref453","article-title":"Seq2sql: Generating structured queries from natural language using reinforcement learning","volume-title":"arXiv preprint","author":"Zhong","year":"2017"},{"key":"2026033012312262700_ref454","doi-asserted-by":"publisher","first-page":"3790","DOI":"10.18653\/v1\/2020.emnlp-main.310","volume-title":"Neural Topic Modeling by Incorporating Document Relationship Graph","author":"Zhou","year":"2020"},{"key":"2026033012312262700_ref455","first-page":"4623","article-title":"Commonsense knowledge aware conversation generation with graph attention","volume-title":"IJCAI","author":"Zhou","year":"2018"},{"key":"2026033012312262700_ref456","doi-asserted-by":"publisher","first-page":"4306","DOI":"10.18653\/v1\/2020.acl-main.397","volume-title":"AMR Parsing with Latent Structural Information","author":"Zhou","year":"2020"},{"key":"2026033012312262700_ref457","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/P18-1061","article-title":"Neural document summarization by jointly learning to score and select sentences","volume-title":"arXiv preprint","author":"Zhou","year":"2018"},{"key":"2026033012312262700_ref458","doi-asserted-by":"publisher","first-page":"1331","DOI":"10.18653\/v1\/P19-1128","volume-title":"Graph Neural Networks with Generated Parameters for Relation Extraction","author":"Zhu","year":"2019"},{"key":"2026033012312262700_ref459","doi-asserted-by":"publisher","first-page":"5459","DOI":"10.18653\/v1\/D19-1548","volume-title":"Modeling Graph Structure in Transformer for Better AMR-to-Text Generation","author":"Zhu","year":"2019"},{"key":"2026033012312262700_ref460","first-page":"5458","volume-title":"Modeling Graph Structure in Transformer for Better AMR-to-Text Generation","author":"Zhu","year":"2019"},{"key":"2026033012312262700_ref461","doi-asserted-by":"publisher","first-page":"4663","DOI":"10.18653\/v1\/D18-1495","volume-title":"GraphBTM: Graph Enhanced Autoencoded Variational Inference for Biterm Topic Model","author":"Zhu","year":"2018"}],"container-title":["Foundations and Trends\u00ae in Machine Learning"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.emerald.com\/ftmal\/article-pdf\/16\/2\/119\/11155826\/2200000096en.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/www.emerald.com\/ftmal\/article-pdf\/16\/2\/119\/11155826\/2200000096en.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T18:10:55Z","timestamp":1777486255000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.emerald.com\/ftmal\/article\/16\/2\/119\/1332421\/Graph-Neural-Networks-for-Natural-Language"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,25]]},"references-count":461,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2023,1,25]]}},"URL":"https:\/\/doi.org\/10.1561\/2200000096","relation":{},"ISSN":["1935-8237","1935-8245"],"issn-type":[{"value":"1935-8237","type":"print"},{"value":"1935-8245","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,1,25]]}}}