{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T02:46:03Z","timestamp":1783737963410,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":61,"publisher":"ACM","funder":[{"name":"the National Natural Science Foundation of China","award":["62376144"],"award-info":[{"award-number":["62376144"]}]},{"name":"the Science and Technol- ogy Cooperation and Exchange Special Project of Shanxi Province","award":["202204041101016"],"award-info":[{"award-number":["202204041101016"]}]},{"name":"the Key Research and Development Project of Shanxi Province","award":["202102020101008"],"award-info":[{"award-number":["202102020101008"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,8,3]]},"DOI":"10.1145\/3711896.3737060","type":"proceedings-article","created":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T13:30:13Z","timestamp":1754055013000},"page":"979-990","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Multi-level Mixture of Experts for Multimodal Entity Linking"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8246-4700","authenticated-orcid":false,"given":"Zhiwei","family":"Hu","sequence":"first","affiliation":[{"name":"School of Computer and Information Technology, Shanxi University, Taiyuan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6117-5459","authenticated-orcid":false,"given":"V\u00edctor","family":"Guti\u00e9rrez-Basulto","sequence":"additional","affiliation":[{"name":"School of Computer Science and Informatics, Cardiff University, Cardiff, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0263-7289","authenticated-orcid":false,"given":"Zhiliang","family":"Xiang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Informatics, Cardiff University, Cardiff, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1545-5553","authenticated-orcid":false,"given":"Ru","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer and Information Technology, Shanxi University, Shanxi, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9779-2088","authenticated-orcid":false,"given":"Jeff Z.","family":"Pan","sequence":"additional","affiliation":[{"name":"ILCC, School of Informatics, University of Edinburgh, Edinburgh, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,8,3]]},"reference":[{"key":"e_1_3_2_2_1_1","first-page":"463","article-title":"Multimodal Entity Linking for Tweets","author":"Adjali Omar","year":"2020","unstructured":"Omar Adjali, Romaric Besan\u00e7on, Olivier Ferret, Herv\u00e9 Le Borgne, and Brigitte Grau. 2020. Multimodal Entity Linking for Tweets. In ECIR. 463-478.","journal-title":"ECIR."},{"key":"e_1_3_2_2_2_1","first-page":"1371","article-title":"ConCET: Entity-Aware Topic Classification for Open-Domain Conversa- tional Agents","author":"Ahmadvand Ali","year":"2019","unstructured":"Ali Ahmadvand, Harshita Sahijwani, Jason Ingyu Choi, and Eugene Agichtein. 2019. ConCET: Entity-Aware Topic Classification for Open-Domain Conversa- tional Agents. In CIKM. 1371-1380.","journal-title":"CIKM."},{"key":"e_1_3_2_2_3_1","unstructured":"Meta AI. 2024. Introducing meta llama 3: The most capable openly available LLM to date."},{"key":"e_1_3_2_2_4_1","volume-title":"Investigating the Robustness of LLMs on Math Word Problems. arXiv","author":"Anantheswaran Ujjwala","year":"2024","unstructured":"Ujjwala Anantheswaran, Himanshu Gupta, Kevin Scaria, Shreyas Verma, Chitta Baral, and Swaroop Mishra. 2024. Investigating the Robustness of LLMs on Math Word Problems. arXiv (2024)."},{"key":"e_1_3_2_2_5_1","first-page":"209","article-title":"ReFinED: An Efficient Zero-shot-capable Approach to End-to-End Entity Linking","author":"Ayoola Tom","year":"2022","unstructured":"Tom Ayoola, Shubhi Tyagi, Joseph Fisher, Christos Christodoulopoulos, and Andrea Pierleoni. 2022. ReFinED: An Efficient Zero-shot-capable Approach to End-to-End Entity Linking. In NAACL. 209-220.","journal-title":"NAACL."},{"key":"e_1_3_2_2_6_1","first-page":"109","article-title":"Penguins in sweaters, or serendipitous entity search on user-generated content","author":"Bordino Ilaria","year":"2013","unstructured":"Ilaria Bordino, Yelena Mejova, and Mounia Lalmas. 2013. Penguins in sweaters, or serendipitous entity search on user-generated content. In CIKM. 109-118.","journal-title":"CIKM."},{"key":"e_1_3_2_2_7_1","first-page":"1","article-title":"Autoregressive Entity Retrieval","author":"Cao Nicola De","year":"2021","unstructured":"Nicola De Cao, Gautier Izacard, Sebastian Riedel, and Fabio Petroni. 2021. Autoregressive Entity Retrieval. In ICLR. 1-20.","journal-title":"ICLR."},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00460"},{"key":"e_1_3_2_2_9_1","first-page":"675","article-title":"Neural Collective Entity Linking","author":"Cao Yixin","year":"2018","unstructured":"Yixin Cao, Lei Hou, Juanzi Li, and Zhiyuan Liu. 2018. Neural Collective Entity Linking. In COLING. 675-686.","journal-title":"COLING."},{"key":"e_1_3_2_2_10_1","first-page":"349","article-title":"Knowledge-based Transfer Learning Explanation","author":"Chen Jiaoyan","year":"2018","unstructured":"Jiaoyan Chen, Freddy Lecue, Jeff Z. Pan, Ian Horrocks, and Huajun Chen. 2018. Knowledge-based Transfer Learning Explanation. In KR. 349-358.","journal-title":"KR."},{"key":"e_1_3_2_2_11_1","first-page":"1724","article-title":"Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation","author":"Cho Kyunghyun","year":"2014","unstructured":"Kyunghyun Cho, Bart van Merrienboer, \u00c7aglar G\u00fcl\u00e7ehre, Dzmitry Bahdanau, Fethi Bougares, Holger Schwenk, and Yoshua Bengio. 2014. Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation. In EMNLP. 1724-1734.","journal-title":"EMNLP."},{"key":"e_1_3_2_2_12_1","first-page":"4171","article-title":"BERT","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In NAACL. 4171-4186.","journal-title":"Pre-training of Deep Bidirectional Transformers for Language Understanding. In NAACL."},{"key":"e_1_3_2_2_13_1","volume-title":"Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, Jakob Uszkoreit, and Neil Houlsby.","author":"Dosovitskiy Alexey","year":"2021","unstructured":"Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xi- aohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, Jakob Uszkoreit, and Neil Houlsby. 2021. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. In ICLR. 1-22."},{"key":"e_1_3_2_2_14_1","first-page":"18145","article-title":"An Empirical Study of Training End-to-End Vision-and- Language Transformers","author":"Dou Zi-Yi","year":"2022","unstructured":"Zi-Yi Dou, Yichong Xu, Zhe Gan, Jianfeng Wang, Shuohang Wang, Lijuan Wang, Chenguang Zhu, Pengchuan Zhang, Lu Yuan, Nanyun Peng, Zicheng Liu, and Michael Zeng. 2022. An Empirical Study of Training End-to-End Vision-and- Language Transformers. In CVPR. 18145-18155.","journal-title":"CVPR."},{"key":"e_1_3_2_2_15_1","volume-title":"Wyner","author":"Fawei Biralatei","year":"2020","unstructured":"Biralatei Fawei, Jeff Z. Pan, Martin J. Kollingbaum, and Adam Z. Wyner. 2020. A Semi-automated Ontology Construction for Legal Question Answering. New Generation Computing (2020), 453-478."},{"key":"e_1_3_2_2_16_1","first-page":"1457","article-title":"Dynami- cally Expandable Graph Convolution for Streaming Recommendation","author":"He Bowei","year":"2023","unstructured":"Bowei He, Xu He, Yingxue Zhang, Ruiming Tang, and Chen Ma. 2023. Dynami- cally Expandable Graph Convolution for Streaming Recommendation. In WWW. 1457-1467.","journal-title":"WWW."},{"key":"e_1_3_2_2_17_1","volume-title":"Pan","author":"Hu Zhiwei","year":"2024","unstructured":"Zhiwei Hu, V\u00edctor Guti\u00e9rrez-Basulto, Ru Li, and Jeff Z. Pan. 2024. Multi-level Matching Network for Multimodal Entity Linking. arXiv (2024)."},{"key":"e_1_3_2_2_18_1","volume-title":"Pan","author":"Hu Zhiwei","year":"2024","unstructured":"Zhiwei Hu, V\u00edctor Guti\u00e9rrez-Basulto, Zhiliang Xiang, Ru Li, and Jeff Z. Pan. 2024. Leveraging Intra-modal and Inter-modal Interaction for Multi-Modal Entity Alignment. arXiv (2024)."},{"key":"e_1_3_2_2_19_1","volume-title":"Prompting Large Language Models with Knowl- edge Graphs for Question Answering involving Long-tail Facts. Knowledge-Based Systems","author":"Huang Wenyu","year":"2025","unstructured":"Wenyu Huang, Guancheng Zhou, Mirella Lapata, Pavlos Vougiouklis, Sebastien Montella, and Jeff Z Pan. 2025. Prompting Large Language Models with Knowl- edge Graphs for Question Answering involving Long-tail Facts. Knowledge-Based Systems (2025)."},{"key":"e_1_3_2_2_20_1","first-page":"5583","article-title":"ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision","author":"Kim Wonjae","year":"2021","unstructured":"Wonjae Kim, Bokyung Son, and Ildoo Kim. 2021. ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision. In ICML. 5583-5594.","journal-title":"ICML."},{"key":"e_1_3_2_2_21_1","first-page":"1595","article-title":"Improving Entity Linking by Modeling Latent Relations between Mentions","author":"Le Phong","year":"2018","unstructured":"Phong Le and Ivan Titov. 2018. Improving Entity Linking by Modeling Latent Relations between Mentions. In ACL. 1595-1604.","journal-title":"ACL."},{"key":"e_1_3_2_2_22_1","first-page":"9694","article-title":"Align before Fuse","author":"Li Junnan","year":"2021","unstructured":"Junnan Li, Ramprasaath R. Selvaraju, Akhilesh Gotmare, Shafiq R. Joty, Caiming Xiong, and Steven Chu-Hong Hoi. 2021. Align before Fuse: Vision and Language Representation Learning with Momentum Distillation. In NeurIPS. 9694-9705.","journal-title":"Vision and Language Representation Learning with Momentum Distillation. In NeurIPS."},{"key":"e_1_3_2_2_23_1","first-page":"801","article-title":"Knowledge-aware Multimodal Dialogue Systems","author":"Liao Lizi","year":"2018","unstructured":"Lizi Liao, Yunshan Ma, Xiangnan He, Richang Hong, and Tat-Seng Chua. 2018. Knowledge-aware Multimodal Dialogue Systems. In MM. 801-809.","journal-title":"MM."},{"key":"e_1_3_2_2_24_1","first-page":"1909","article-title":"UniMEL","author":"Liu Qi","year":"2024","unstructured":"Qi Liu, Yongyi He, Tong Xu, Defu Lian, Che Liu, Zhi Zheng, and Enhong Chen. 2024. UniMEL: A Unified Framework for Multimodal Entity Linking with Large Language Models. In CIKM. 1909-1919.","journal-title":"In CIKM."},{"key":"e_1_3_2_2_25_1","first-page":"1120","article-title":"Mask and Reason","author":"Liu Xiao","year":"2022","unstructured":"Xiao Liu, Shiyu Zhao, Kai Su, Yukuo Cen, Jiezhong Qiu, Mengdi Zhang, Wei Wu, Yuxiao Dong, and Jie Tang. 2022. Mask and Reason: Pre-Training Knowledge Graph Transformers for Complex Logical Queries. In KDD. 1120-1130.","journal-title":"Pre-Training Knowledge Graph Transformers for Complex Logical Queries. In KDD."},{"key":"e_1_3_2_2_26_1","volume-title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach. arXiv","author":"Liu Yinhan","year":"2019","unstructured":"Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. 2019. RoBERTa: A Robustly Optimized BERT Pretraining Approach. arXiv (2019)."},{"key":"e_1_3_2_2_27_1","first-page":"7559","article-title":"Trust in Internal or External Knowledge","author":"Long Xinwei","year":"2024","unstructured":"Xinwei Long, Jiali Zeng, Fandong Meng, Jie Zhou, and Bowen Zhou. 2024. Trust in Internal or External Knowledge? Generative Multi-Modal Entity Linking with Knowledge Retriever. In ACL. 7559-7569.","journal-title":"Generative Multi-Modal Entity Linking with Knowledge Retriever. In ACL."},{"key":"e_1_3_2_2_28_1","first-page":"7052","article-title":"Entity-Based Knowledge Conflicts in Question Answer- ing","author":"Longpre Shayne","year":"2021","unstructured":"Shayne Longpre, Kartik Perisetla, Anthony Chen, Nikhil Ramesh, Chris DuBois, and Sameer Singh. 2021. Entity-Based Knowledge Conflicts in Question Answer- ing. In EMNLP. 7052-7063.","journal-title":"EMNLP."},{"key":"e_1_3_2_2_29_1","first-page":"1","article-title":"Decoupled Weight Decay Regularization","author":"Loshchilov Ilya","year":"2019","unstructured":"Ilya Loshchilov and Frank Hutter. 2019. Decoupled Weight Decay Regularization. In ICLR. 1-11.","journal-title":"ICLR."},{"key":"e_1_3_2_2_30_1","first-page":"9311","article-title":"Bridging Gaps in Content and Knowledge for Multimodal Entity Linking","author":"Luo Pengfei","year":"2024","unstructured":"Pengfei Luo, Tong Xu, Che Liu, Suojuan Zhang, Linli Xu, Minglei Li, and Enhong Chen. 2024. Bridging Gaps in Content and Knowledge for Multimodal Entity Linking. In MM. 9311-9320.","journal-title":"MM."},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"crossref","unstructured":"Pengfei Luo Tong Xu Shiwei Wu Chen Zhu Linli Xu and Enhong Chen. 2023. Multi-Grained Multimodal Interaction Network for Entity Linking. In KDD. 1583- 1594.","DOI":"10.1145\/3580305.3599439"},{"key":"e_1_3_2_2_32_1","first-page":"2000","article-title":"Multimodal Named Entity Disambiguation for Noisy Social Media Posts","author":"Moon Seungwhan","year":"2018","unstructured":"Seungwhan Moon, Leonardo Neves, and Vitor Carvalho. 2018. Multimodal Named Entity Disambiguation for Noisy Social Media Posts. In ACL. 2000-2008.","journal-title":"ACL."},{"key":"e_1_3_2_2_33_1","unstructured":"OpenAI. 2023. Chatgpt."},{"key":"e_1_3_2_2_34_1","first-page":"669","article-title":"Reducing Ambiguity in Tagging Systems with Folksonomy Search Expansion","author":"Pan Jeff","year":"2009","unstructured":"Jeff Pan, Stuart Taylor, and Edward Thomas. 2009. Reducing Ambiguity in Tagging Systems with Folksonomy Search Expansion. In ESWC. 669-683.","journal-title":"ESWC."},{"key":"e_1_3_2_2_35_1","volume-title":"Jose Manuel Gomez-Perez","author":"Pan Jeff Z.","year":"2017","unstructured":"Jeff Z. Pan, Guido Vetere, Jose Manuel Gomez-Perez, and Honghan Wu (Eds.). 2017. Exploiting Linked Data and Knowledge Graphs for Large Organisations. Springer."},{"key":"e_1_3_2_2_36_1","first-page":"523","article-title":"Entity Enabled Relation Linking","author":"Pan Jeff Z.","year":"2019","unstructured":"Jeff Z. Pan, Mei Zhang, Kuldeep Singh, Frank Van Harmelen, Jinguang Gu, and Zhi Zhang. 2019. Entity Enabled Relation Linking. In ISWC. 523-538.","journal-title":"ISWC."},{"key":"e_1_3_2_2_37_1","first-page":"43","article-title":"Knowledge Enhanced Contextual Word Representations","author":"Peters Matthew E.","year":"2019","unstructured":"Matthew E. Peters, Mark Neumann, Robert L. Logan IV, Roy Schwartz, Vidur Joshi, Sameer Singh, and Noah A. Smith. 2019. Knowledge Enhanced Contextual Word Representations. In EMNLP. 43-54.","journal-title":"EMNLP."},{"key":"e_1_3_2_2_38_1","volume-title":"Assessing the Emergent Symbolic Reasoning Abilities of Llama Large Language Models. arXiv","author":"Petruzzellis Flavio","year":"2024","unstructured":"Flavio Petruzzellis, Alberto Testolin, and Alessandro Sperduti. 2024. Assessing the Emergent Symbolic Reasoning Abilities of Llama Large Language Models. arXiv (2024)."},{"key":"e_1_3_2_2_39_1","first-page":"8748","article-title":"Learning Transferable Visual Models From Natural Language Supervision","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, Gretchen Krueger, and Ilya Sutskever. 2021. Learning Transferable Visual Models From Natural Language Supervision. In ICML. 8748-8763.","journal-title":"ICML."},{"key":"e_1_3_2_2_40_1","first-page":"1135","article-title":"An Attention Factor Graph Model for Tweet Entity Linking","author":"Ran Chenwei","year":"2018","unstructured":"Chenwei Ran, Wei Shen, and Jianyong Wang. 2018. An Attention Factor Graph Model for Tweet Entity Linking. In WWW. 1135-1144.","journal-title":"WWW."},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.63317\/48465grj4cjm"},{"key":"e_1_3_2_2_42_1","first-page":"1","article-title":"Very Deep Convolutional Net- works for Large-Scale Image Recognition","author":"Simonyan Karen","year":"2015","unstructured":"Karen Simonyan and Andrew Zisserman. 2015. Very Deep Convolutional Net- works for Large-Scale Image Recognition. In ICLR. 1-14.","journal-title":"ICLR."},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i17.29867"},{"key":"e_1_3_2_2_44_1","first-page":"816","article-title":"MELOV: Multimodal Entity Linking with Optimized Visual Features in Latent Space","author":"Sui Xuhui","year":"2024","unstructured":"Xuhui Sui, Ying Zhang, Yu Zhao, Kehui Song, Baohang Zhou, and Xiaojie Yuan. 2024. MELOV: Multimodal Entity Linking with Optimized Visual Features in Latent Space. In ACL. 816-826.","journal-title":"ACL."},{"key":"e_1_3_2_2_45_1","volume-title":"Sleeman","author":"Thomas Edward","year":"2007","unstructured":"Edward Thomas, Jeff Z. Pan, and Derek H. Sleeman. 2007. ONTOSEARCH2: Searching Ontologies Semantically.. In OWLED."},{"key":"e_1_3_2_2_46_1","volume-title":"LLaMA: Open and Efficient Foundation Language Models. arXiv","author":"Touvron Hugo","year":"2023","unstructured":"Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timoth\u00e9e Lacroix, Baptiste Rozi\u00e8re, Naman Goyal, Eric Hambro, Faisal Azhar, Aur\u00e9lien Rodriguez, Armand Joulin, Edouard Grave, and Guillaume Lam- ple. 2023. LLaMA: Open and Efficient Foundation Language Models. arXiv (2023)."},{"key":"e_1_3_2_2_47_1","unstructured":"Hugo Touvron Louis Martin Kevin Stone Peter Albert Amjad Almahairi Yas- mine Babaei Nikolay Bashlykov Soumya Batra Prajjwal Bhargava Shruti Bhos- ale Dan Bikel Lukas Blecher Cristian Canton-Ferrer Moya Chen Guillem Cucu- rull David Esiobu Jude Fernandes Jeremy Fu Wenyin Fu Brian Fuller Cynthia Gao Vedanuj Goswami Naman Goyal Anthony Hartshorn Saghar Hosseini Rui Hou Hakan Inan Marcin Kardas Viktor Kerkez Madian Khabsa Isabel Kloumann Artem Korenev Punit Singh Koura Marie-Anne Lachaux Thibaut Lavril Jenya Lee Diana Liskovich Yinghai Lu Yuning Mao Xavier Martinet Todor Mihaylov Pushkar Mishra Igor Molybog Yixin Nie Andrew Poulton Jeremy Reizenstein Rashi Rungta Kalyan Saladi Alan Schelten Ruan Silva Eric Michael Smith Ranjan Subramanian Xiaoqing Ellen Tan Binh Tang Ross Taylor Adina Williams Jian Xiang Kuan Puxin Xu Zheng Yan Iliyan Zarov Yuchen Zhang Angela Fan Melanie Kambadur Sharan Narang Aur\u00e9lien Ro- driguez Robert Stojnic Sergey Edunov and Thomas Scialom. 2023. Llama 2: Open Foundation and Fine-Tuned Chat Models. arXiv (2023)."},{"key":"e_1_3_2_2_48_1","first-page":"5998","article-title":"Attention is All you Need","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser, and Illia Polosukhin. 2017. Attention is All you Need. In NeurIPS. 5998-6008.","journal-title":"NeurIPS."},{"key":"e_1_3_2_2_49_1","volume-title":"Wikidata: a free collaborative knowledgebase. Commun. ACM","author":"Vrandecic Denny","year":"2014","unstructured":"Denny Vrandecic and Markus Kr\u00f6tzsch. 2014. Wikidata: a free collaborative knowledgebase. Commun. ACM (2014), 78-85."},{"key":"e_1_3_2_2_50_1","doi-asserted-by":"crossref","unstructured":"HongruWang WenyuHuang YufeiWang YuanhaoXi JianqiaoLu HuanZhang Nan Hu Zeming Liu Jeff Z. Pan and Kam-Fai Wong. 2025. Rethinking Stateful Tool Use in Multi-Turn Dialogues: Benchmarks and Challenges. In ACL.","DOI":"10.18653\/v1\/2025.findings-acl.284"},{"key":"e_1_3_2_2_51_1","volume-title":"Richpedia: A Large-Scale, Comprehensive Multi-Modal Knowledge Graph. Big Data Res.","author":"Wang Meng","year":"2020","unstructured":"Meng Wang, Haofen Wang, Guilin Qi, and Qiushuo Zheng. 2020. Richpedia: A Large-Scale, Comprehensive Multi-Modal Knowledge Graph. Big Data Res. (2020), 1-11."},{"key":"e_1_3_2_2_52_1","first-page":"938","article-title":"Multimodal Entity Linking with Gated Hierarchical Fusion and Contrastive Training","author":"Wang Peng","year":"2022","unstructured":"Peng Wang, Jiangheng Wu, and Xiaohang Chen. 2022. Multimodal Entity Linking with Gated Hierarchical Fusion and Contrastive Training. In SIGIR. 938-948.","journal-title":"SIGIR."},{"key":"e_1_3_2_2_53_1","first-page":"4785","article-title":"WikiDiverse","author":"Wang Xuwu","year":"2022","unstructured":"Xuwu Wang, Junfeng Tian, Min Gui, Zhixu Li, Rui Wang, Ming Yan, Lihan Chen, and Yanghua Xiao. 2022. WikiDiverse: A Multimodal Entity Linking Dataset with Diversified Contextual Topics and Entity Types. In ACL. 4785-4797.","journal-title":"In ACL."},{"key":"e_1_3_2_2_54_1","first-page":"6397","article-title":"Scalable Zero-shot Entity Linking with Dense Entity Retrieval","author":"Wu Ledell","year":"2020","unstructured":"Ledell Wu, Fabio Petroni, Martin Josifoski, Sebastian Riedel, and Luke Zettlemoyer. 2020. Scalable Zero-shot Entity Linking with Dense Entity Retrieval. In EMNLP. 6397-6407.","journal-title":"EMNLP."},{"key":"e_1_3_2_2_55_1","first-page":"4258","article-title":"Improving Question Answering over Incomplete KBs with Knowledge- Aware Reader","author":"Xiong Wenhan","year":"2019","unstructured":"Wenhan Xiong, Mo Yu, Shiyu Chang, Xiaoxiao Guo, and William Yang Wang. 2019. Improving Question Answering over Incomplete KBs with Knowledge- Aware Reader. In ACL. 4258-4264.","journal-title":"ACL."},{"key":"e_1_3_2_2_56_1","first-page":"3160","article-title":"Multimodal Knowledge Learning for Named Entity Disambiguation","author":"Zhang Dongjie","year":"2022","unstructured":"Dongjie Zhang and Longtao Huang. 2022. Multimodal Knowledge Learning for Named Entity Disambiguation. In EMNLP. 3160-3169.","journal-title":"EMNLP."},{"key":"e_1_3_2_2_57_1","first-page":"607","article-title":"Multimodal Entity Linking with Mixed Fusion Mechanism","author":"Zhang Gongrui","year":"2023","unstructured":"Gongrui Zhang, Chenghuan Jiang, Zhongheng Guan, and Peng Wang. 2023. Multimodal Entity Linking with Mixed Fusion Mechanism. In DASFAA. 607-622.","journal-title":"DASFAA."},{"key":"e_1_3_2_2_58_1","first-page":"533","article-title":"Attention-Based Multimodal Entity Linking with High-Quality Images","author":"Zhang Li","year":"2021","unstructured":"Li Zhang, Zhixu Li, and Qiang Yang. 2021. Attention-Based Multimodal Entity Linking with High-Quality Images. In DASFAA. 533-548.","journal-title":"DASFAA."},{"key":"e_1_3_2_2_59_1","first-page":"4103","article-title":"Optimal Transport Guided Correlation Assignment for Multimodal Entity Linking","author":"Zhang Zefeng","year":"2024","unstructured":"Zefeng Zhang, Jiawei Sheng, Chuang Zhang, Liangyunzhi Liangyunzhi, Wenyuan Zhang, Siqi Wang, and Tingwen Liu. 2024. Optimal Transport Guided Correlation Assignment for Multimodal Entity Linking. In ACL. 4103-4117.","journal-title":"ACL."},{"key":"e_1_3_2_2_60_1","doi-asserted-by":"crossref","unstructured":"Qiushuo Zheng Hao Wen Meng Wang and Guilin Qi. 2022. Visual Entity Linking via Multi-modal Learning. Data Intell. (2022) 1-19.","DOI":"10.1162\/dint_a_00114"},{"key":"e_1_3_2_2_61_1","doi-asserted-by":"crossref","unstructured":"Jeff Z.Pan Diego Calvanese Thomas Eiter Ian Horrocks Michael Kifer Fangzhen Lin andYutingZhao(Eds.).2017. ReasoningWeb:LogicalFoundationofKnowledge Graph Construction and Querying Answering. Springer.","DOI":"10.1007\/978-3-319-49493-7"}],"event":{"name":"KDD '25: The 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Toronto ON Canada","acronym":"KDD '25","sponsor":["SIGKDD ACM Special Interest Group on Knowledge Discovery in Data","SIGMOD ACM Special Interest Group on Management of Data"]},"container-title":["Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3711896.3737060","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T18:19:29Z","timestamp":1777573169000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3711896.3737060"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,3]]},"references-count":61,"alternative-id":["10.1145\/3711896.3737060","10.1145\/3711896"],"URL":"https:\/\/doi.org\/10.1145\/3711896.3737060","relation":{},"subject":[],"published":{"date-parts":[[2025,8,3]]},"assertion":[{"value":"2025-08-03","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}