{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T13:07:32Z","timestamp":1781096852774,"version":"3.54.1"},"reference-count":47,"publisher":"Association for Computing Machinery (ACM)","issue":"2","license":[{"start":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T00:00:00Z","timestamp":1781049600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"RPI-Stevens NSF IUCRC Center for Research toward Advancing Financial Technologies","award":["NSF Award #: 2113850"],"award-info":[{"award-number":["NSF Award #: 2113850"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Manage. Inf. Syst."],"published-print":{"date-parts":[[2026,6,30]]},"abstract":"<jats:p>Language models (LMs) have shown great promise in generative and predictive tasks. However, they do not explicitly incorporate semantic relations, and despite the progress in increasing the context size, they still struggle with long documents. Since abstract meaning representation (AMR), which is a graph-based representation of text to preserve its semantic relations, can encode semantic relationships at a deeper level, it can be beneficially utilized by graph neural networks (GNNs) for constructing effective document-level graph representations built upon LM embeddings for predictive tasks. We propose FLAG, an AMR-based framework to generate document-level embeddings via GNNs for long document classification tasks. We construct document-level graphs from sentence-level AMR graphs, endow them with finance-specific LM word embeddings, apply a GNN-based deep learning mechanism, and examine the efficacy of our AMR-based approach in predicting trends from financial documents. Extensive experiments on several different tasks are conducted on two large datasets of quarterly earnings call transcripts. We find that FLAG outperforms fine-tuning LMs directly on text in predicting stock price movement trends, as well as previous work utilizing document graphs and GNNs for text classification. Finally, we demonstrate our AMR-graph-based approach\u2019s potential for explainability via a case study.<\/jats:p>","DOI":"10.1145\/3810185","type":"journal-article","created":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T11:25:16Z","timestamp":1776425116000},"page":"1-27","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Semantic Graph Based Learning for Trend Prediction from Long Financial Documents"],"prefix":"10.1145","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6841-9017","authenticated-orcid":false,"given":"Bolun (Namir)","family":"Xia","sequence":"first","affiliation":[{"name":"Computer Science, Rensselaer Polytechnic Institute","place":["Troy, United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5275-7756","authenticated-orcid":false,"given":"Aparna","family":"Gupta","sequence":"additional","affiliation":[{"name":"Lally School of Management, Rensselaer Polytechnic Institute","place":["Troy, United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4711-0234","authenticated-orcid":false,"given":"Mohammed J","family":"Zaki","sequence":"additional","affiliation":[{"name":"Computer Science, Rensselaer Polytechnic Institute","place":["Troy, United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,6,10]]},"reference":[{"key":"e_1_3_1_2_2","unstructured":"AIMeta. 2024. Llama 3 Model Card. Retrieved from https:\/\/github.com\/meta-llama\/llama3\/blob\/main\/MODEL_CARD.md"},{"key":"e_1_3_1_3_2","doi-asserted-by":"publisher","unstructured":"arXiv.org submitters. 2024. arXiv Dataset. DOI:10.34740\/KAGGLE\/DSV\/7548853","DOI":"10.34740\/KAGGLE\/DSV\/7548853"},{"key":"e_1_3_1_4_2","first-page":"178","volume-title":"Proceedings of the 7th Linguistic Annotation Workshop and Interoperability with Discourse","author":"Banarescu Laura","year":"2013","unstructured":"Laura Banarescu, Claire Bonial, Shu Cai, Madalina Georgescu, Kira Griffitt, Ulf Hermjakob, Kevin Knight, Philipp Koehn, Martha Palmer, and Nathan Schneider. 2013. Abstract meaning representation for sembanking. In Proceedings of the 7th Linguistic Annotation Workshop and Interoperability with Discourse. 178\u2013186."},{"key":"e_1_3_1_5_2","volume-title":"Proceedings of the 1st Conference on Language Modeling","author":"BehnamGhader Parishad","year":"2024","unstructured":"Parishad BehnamGhader, Vaibhav Adlakha, Marius Mosbach, Dzmitry Bahdanau, Nicolas Chapados, and Siva Reddy. 2024. LLM2Vec: Large language models are secretly powerful text encoders. In Proceedings of the 1st Conference on Language Modeling. Retrieved from https:\/\/openreview.net\/forum?id=IW1PR7vEBf"},{"key":"e_1_3_1_6_2","unstructured":"Iz Beltagy Matthew E. Peters and Arman Cohan. 2020. Longformer: The long-document transformer. arxiv:2004.05150. Retrieved from https:\/\/arxiv.org\/abs\/2004.05150"},{"key":"e_1_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.3115\/1219044.1219075"},{"key":"e_1_3_1_8_2","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Brody Shaked","year":"2022","unstructured":"Shaked Brody, Uri Alon, and Eran Yahav. 2022. How attentive are graph attention networks?. In Proceedings of the International Conference on Learning Representations."},{"key":"e_1_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.297"},{"key":"e_1_3_1_10_2","unstructured":"James Chen. 2021. Earnings call. Retrieved from https:\/\/www.investopedia.com\/terms\/e\/earnings-call.asp"},{"key":"e_1_3_1_11_2","volume-title":"Proceedings of the Advances in Neural Information Processing Systems","author":"Corso Gabriele","year":"2020","unstructured":"Gabriele Corso, Luca Cavalleri, Dominique Beaini, Pietro Li\u00f2, and Petar Veli\u010dkovi\u0107. 2020. Principal neighbourhood aggregation for graph nets. In Proceedings of the Advances in Neural Information Processing Systems."},{"key":"e_1_3_1_12_2","unstructured":"Jacob Devlin Ming-Wei Chang Kenton Lee and Kristina Toutanova. 2018. BERT: Pre-training of deep bidirectional transformers for language understanding. arxiv:1810.04805. Retrieved from https:\/\/arxiv.org\/abs\/1810.04805"},{"key":"e_1_3_1_13_2","first-page":"1086","volume-title":"Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","author":"Drozdov Andrew","year":"2022","unstructured":"Andrew Drozdov, Jiawei Zhou, Radu Florian, Andrew McCallum, Tahira Naseem, Yoon Kim, and Ram\u00f3n Astudillo. 2022. Inducing and using alignments for transition-based AMR parsing. In Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 1086\u20131098."},{"key":"e_1_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.13052\/jwe1540-9589.2135"},{"key":"e_1_3_1_15_2","unstructured":"Fama-French. 2025. Retrieved from https:\/\/mba.tuck.dartmouth.edu\/pages\/faculty\/ken.french\/ftp\/F-F_Research_Data_Factors_daily_CSV.zip"},{"key":"e_1_3_1_16_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-naacl.55"},{"key":"e_1_3_1_17_2","unstructured":"S&P Dow Jones Indices. 2025. Retrieved from https:\/\/www.spglobal.com\/spdji\/en\/indices\/equity\/sp-composite-1500\/#overview"},{"key":"e_1_3_1_18_2","unstructured":"Pranab Islam Anand Kannappan Douwe Kiela Rebecca Qian Nino Scherrer and Bertie Vidgen. 2023. FinanceBench: A new benchmark for financial question answering. arxiv:2311.11944. Retrieved from https:\/\/arxiv.org\/abs\/2311.11944"},{"key":"e_1_3_1_19_2","unstructured":"Albert Q. Jiang Alexandre Sablayrolles Arthur Mensch Chris Bamford Devendra Singh Chaplot Diego de las Casas Florian Bressand Gianna Lengyel Guillaume Lample Lucile Saulnier et\u00a0al. 2023. Mistral 7B. arxiv:2310.06825. Retrieved from https:\/\/arxiv.org\/abs\/2310.06825"},{"key":"e_1_3_1_20_2","doi-asserted-by":"publisher","unstructured":"Alistair Johnson Lucas Bulgarelli Tom Pollard Steven Horng Leo Anthony Celi and Roger Mark. 2021. MIMIC-IV. PhysioNet. RRID:SCR_007345. DOI:10.13026\/s6n6-xd98","DOI":"10.13026\/s6n6-xd98"},{"key":"e_1_3_1_21_2","doi-asserted-by":"publisher","DOI":"10.1038\/sdata.2016.35"},{"key":"e_1_3_1_22_2","volume-title":"Speech and Language Processing (3 (draft) ed.)","author":"Jurafsky Dan","year":"2024","unstructured":"Dan Jurafsky and James H. Martin. 2024. Speech and Language Processing (3 (draft) ed.). Retrieved from https:\/\/web.stanford.edu\/jurafsky\/slp3\/"},{"key":"e_1_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.5555\/3044805.3045025"},{"key":"e_1_3_1_24_2","first-page":"3254","volume-title":"Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","author":"Lee John Sie Yuen","year":"2022","unstructured":"John Sie Yuen Lee, Ho Hung Lim, and Carol Webster. 2022. Unsupervised paraphrasability prediction for compound nominalizations. In Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 3254\u20133263."},{"key":"e_1_3_1_25_2","first-page":"5379","volume-title":"Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","author":"Lee Young-Suk","year":"2022","unstructured":"Young-Suk Lee, Ram\u00f3n Astudillo, Hoang Thanh Lam, Tahira Naseem, Radu Florian, and Salim Roukos. 2022. Maximum bayes smatch ensemble distillation for AMR parsing. In Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 5379\u20135392."},{"key":"e_1_3_1_26_2","first-page":"12","volume-title":"Proceedings of the 2nd Workshop on Deep Learning on Graphs for Natural Language Processing (DLG4NLP 2022)","author":"Li Changmao","year":"2022","unstructured":"Changmao Li and Jeffrey Flanigan. 2022. Improving neural machine translation with the abstract meaning representation by combining graph and sequence transformers. In Proceedings of the 2nd Workshop on Deep Learning on Graphs for Natural Language Processing (DLG4NLP 2022). 12\u201321."},{"key":"e_1_3_1_27_2","volume-title":"Proceedings of the Association for Computational Linguistics (ACL)","author":"Li Irene","year":"2023","unstructured":"Irene Li, Aosong Feng, Dragomir Radev, and Rex Ying. 2023. HiPool: Modeling long documents using graph neural networks. In Proceedings of the Association for Computational Linguistics (ACL)."},{"key":"e_1_3_1_28_2","first-page":"11","volume-title":"Proceedings of the 1st Workshop on Computing News Storylines","author":"Li Xiang","year":"2015","unstructured":"Xiang Li, Thien Huu Nguyen, Kai Cao, and Ralph Grishman. 2015. Improving event detection with abstract meaning representation. In Proceedings of the 1st Workshop on Computing News Storylines. 11\u201315."},{"key":"e_1_3_1_29_2","volume-title":"Proceedings of the 4th International Conference on Learning Representations","author":"Li Yujia","year":"2016","unstructured":"Yujia Li, Daniel Tarlow, Marc Brockschmidt, and Richard S. Zemel. 2016. Gated graph sequence neural networks. In Proceedings of the 4th International Conference on Learning Representations."},{"key":"e_1_3_1_30_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS60910.2024.00036"},{"key":"e_1_3_1_31_2","unstructured":"Debanjan Mahata Navneet Agarwal Dibya Gautam Amardeep Kumar Swapnil Parekh Yaman Kumar Singla Anish Acharya and Rajiv Ratn Shah. 2022. LDKP: A Dataset for Identifying Keyphrases from Long Scientific Documents. arxiv:2203.15349. Retrieved from https:\/\/arxiv.org\/abs\/2203.15349"},{"key":"e_1_3_1_32_2","doi-asserted-by":"publisher","DOI":"10.1145\/3487553.3524205"},{"key":"e_1_3_1_33_2","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Mikolov Tomas","year":"2013","unstructured":"Tomas Mikolov, Kai Chen, Gregory S. Corrado, and Jeffrey Dean. 2013. Efficient estimation of word representations in vector space. In Proceedings of the International Conference on Learning Representations."},{"key":"e_1_3_1_34_2","first-page":"3496","volume-title":"Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","author":"Naseem Tahira","year":"2022","unstructured":"Tahira Naseem, Austin Blodgett, Sadhana Kumaravel, Tim O\u2019Gorman, Young-Suk Lee, Jeffrey Flanigan, Ram\u00f3n Astudillo, Radu Florian, Salim Roukos, and Nathan Schneider. 2022. DocAMR: Multi-sentence AMR representation and evaluation. In Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 3496\u20133505."},{"key":"e_1_3_1_35_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1451"},{"key":"e_1_3_1_36_2","first-page":"3693","volume-title":"Proceedings of the 27th International Conference on Computational Linguistics","author":"O\u2019Gorman Tim","year":"2018","unstructured":"Tim O\u2019Gorman, Michael Regan, Kira Griffitt, Ulf Hermjakob, Kevin Knight, and Martha Palmer. 2018. AMR beyond the sentence: The multi-sentence AMR corpus. In Proceedings of the 27th International Conference on Computational Linguistics. 3693\u20133702."},{"key":"e_1_3_1_37_2","unstructured":"OpenAI. 2024. GPT-4 technical report. arxiv:2303.08774. Retrieved from https:\/\/arxiv.org\/abs\/2303.08774"},{"key":"e_1_3_1_38_2","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"issue":"3","key":"e_1_3_1_39_2","first-page":"425","article-title":"Capital asset prices: A theory of market equilibrium under conditions of risk","volume":"19","author":"Sharpe William F.","year":"1964","unstructured":"William F. Sharpe. 1964. Capital asset prices: A theory of market equilibrium under conditions of risk. The Journal of Finance 19, 3 (1964), 425\u2013442.","journal-title":"The Journal of Finance"},{"key":"e_1_3_1_40_2","doi-asserted-by":"crossref","first-page":"3082","DOI":"10.18653\/v1\/2022.findings-acl.244","volume-title":"Findings of the Association for Computational Linguistics: ACL 2022","author":"Shou Ziyi","year":"2022","unstructured":"Ziyi Shou, Yuxin Jiang, and Fangzhen Lin. 2022. AMR-DA: Data augmentation by abstract meaning representation. In Findings of the Association for Computational Linguistics: ACL 2022. 3082\u20133098."},{"key":"e_1_3_1_41_2","first-page":"1235","volume-title":"Proceedings of the 12th Language Resources and Evaluation Conference","author":"Tuggener Don","year":"2020","unstructured":"Don Tuggener, Pius von D\u00e4niken, Thomas Peetz, and Mark Cieliebak. 2020. LEDGAR: A large-scale multi-label corpus for text classification of legal provisions in contracts. In Proceedings of the 12th Language Resources and Evaluation Conference. Nicoletta Calzolari, Fr\u00e9d\u00e9ric B\u00e9chet, Philippe Blache, Khalid Choukri, Christopher Cieri, Thierry Declerck, Sara Goggi, Hitoshi Isahara, Bente Maegaard, Joseph Mariani, H\u00e9l\u00e8ne Mazo, Asuncion Moreno, Jan Odijk, and Stelios Piperidis (Eds.), European Language Resources Association, Marseille, France, 1235\u20131241. Retrieved from https:\/\/aclanthology.org\/2020.lrec-1.155\/"},{"key":"e_1_3_1_42_2","article-title":"Graph attention networks","author":"Veli\u010dkovi\u0107 Petar","year":"2018","unstructured":"Petar Veli\u010dkovi\u0107, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Li\u00f2, and Yoshua Bengio. 2018. Graph attention networks. International Conference on Learning Representations (2018).","journal-title":"International Conference on Learning Representations"},{"key":"e_1_3_1_43_2","unstructured":"Minjie Wang Da Zheng Zihao Ye Quan Gan Mufei Li Xiang Song Jinjing Zhou Chao Ma Lingfan Yu Yu Gai et\u00a0al. 2019. Deep graph library: A graph-centric highly-performant package for graph neural networks. arxiv:1909.01315. Retrieved from https:\/\/arxiv.org\/abs\/1909.01315"},{"key":"e_1_3_1_44_2","unstructured":"Shijie Wu Ozan Irsoy Steven Lu Vadim Dabravolski Mark Dredze Sebastian Gehrmann Prabhanjan Kambadur David Rosenberg and Gideon Mann. 2023. BloombergGPT: A large language model for finance. arxiv:2303.17564. Retrieved from https:\/\/arxiv.org\/abs\/2303.17564"},{"key":"e_1_3_1_45_2","doi-asserted-by":"crossref","unstructured":"Hongyang Yang Xiao-Yang Liu and Christina Dan Wang. 2023. FinGPT: Open-source financial large language models. arxiv:2306.06031. Retrieved from https:\/\/arxiv.org\/abs\/2306.06031","DOI":"10.2139\/ssrn.4489826"},{"key":"e_1_3_1_46_2","unstructured":"Yi Yang Mark Christopher Siy UY and Allen Huang. 2020. FinBERT: A pretrained language model for financial communications. arxiv:2006.08097. Retrieved from https:\/\/arxiv.org\/abs\/2006.08097"},{"key":"e_1_3_1_47_2","volume-title":"Proceedings of the 33rd International Conference on Neural Information Processing Systems","author":"Ying Rex","year":"2019","unstructured":"Rex Ying, Dylan Bourgeois, Jiaxuan You, Marinka Zitnik, and Jure Leskovec. 2019. GNNExplainer: Generating explanations for graph neural networks. In Proceedings of the 33rd International Conference on Neural Information Processing Systems."},{"key":"e_1_3_1_48_2","first-page":"6279","volume-title":"Proceedings of the Conference on Empirical Methods in Natural Language Processing","author":"Zhou Jiawei","year":"2021","unstructured":"Jiawei Zhou, Tahira Naseem, Ram\u00f3n Fernandez Astudillo, Young-Suk Lee, Radu Florian, and Salim Roukos. 2021. Structure-aware fine-tuning of sequence-to-sequence transformers for transition-based AMR parsing. In Proceedings of the Conference on Empirical Methods in Natural Language Processing. 6279\u20136290."}],"container-title":["ACM Transactions on Management Information Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3810185","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T12:36:07Z","timestamp":1781094967000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3810185"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,10]]},"references-count":47,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,6,30]]}},"alternative-id":["10.1145\/3810185"],"URL":"https:\/\/doi.org\/10.1145\/3810185","relation":{},"ISSN":["2158-656X","2158-6578"],"issn-type":[{"value":"2158-656X","type":"print"},{"value":"2158-6578","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,10]]},"assertion":[{"value":"2025-02-20","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-04-05","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-06-10","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}