{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,23]],"date-time":"2026-03-23T22:11:24Z","timestamp":1774303884049,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":33,"publisher":"ACM","funder":[{"name":"Information & Communications Technology Planning & Evaluation","award":["RS-2024-00438638, RS-2022-II220871, IITP-2025-RS-2023-00253914, RS-2019-II190075"],"award-info":[{"award-number":["RS-2024-00438638, RS-2022-II220871, IITP-2025-RS-2023-00253914, RS-2019-II190075"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,7,13]]},"DOI":"10.1145\/3726302.3730217","type":"proceedings-article","created":{"date-parts":[[2025,7,14]],"date-time":"2025-07-14T01:38:52Z","timestamp":1752457132000},"page":"3015-3019","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["KGMEL: Knowledge Graph-Enhanced Multimodal Entity Linking"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-6102-6589","authenticated-orcid":false,"given":"Juyeon","family":"Kim","sequence":"first","affiliation":[{"name":"KAIST, Seoul, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6339-9758","authenticated-orcid":false,"given":"Geon","family":"Lee","sequence":"additional","affiliation":[{"name":"KAIST, Seoul, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6919-7727","authenticated-orcid":false,"given":"Taeuk","family":"Kim","sequence":"additional","affiliation":[{"name":"Hanyang University, Seoul, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2872-1526","authenticated-orcid":false,"given":"Kijung","family":"Shin","sequence":"additional","affiliation":[{"name":"KAIST, Seoul, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,7,13]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"Herv\u00e9 Le Borgne, and Brigitte Grau","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."},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"crossref","unstructured":"Ilaria Bordino Yelena Mejova and Mounia Lalmas. 2013. Penguins in sweaters or serendipitous entity search on user-generated content. In CIKM.","DOI":"10.1145\/2505515.2505680"},{"key":"e_1_3_2_2_3_1","volume-title":"Entityrank: Searching entities directly and holistically. In VLDB.","author":"Cheng Tao","year":"2007","unstructured":"Tao Cheng, Xifeng Yan, and Kevin Chen-Chuan Chang. 2007. Entityrank: Searching entities directly and holistically. In VLDB."},{"key":"e_1_3_2_2_4_1","unstructured":"Wen Cui Leanne Rolston Marilyn Walker and Beth Ann Hockey. 2022. OpenEL: An annotated corpus for entity linking and discourse in open domain dialogue. In LREC-COLING."},{"key":"e_1_3_2_2_5_1","unstructured":"Amanda Cercas Curry Ioannis Papaioannou Alessandro Suglia Shubham Agarwal Igor Shalyminov Xinnuo Xu Ondrej Du\u0161ek Arash Eshghi Ioannis Konstas Verena Rieser et al. 2018. Alana v2: Entertaining and informative open-domain social dialogue using ontologies and entity linking. In Alexa prize proceedings. 26."},{"key":"e_1_3_2_2_6_1","volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding. In ACL.","author":"Devlin Jacob","year":"2018","unstructured":"Jacob Devlin. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. In ACL."},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"crossref","unstructured":"Zi-Yi Dou Yichong Xu Zhe Gan Jianfeng Wang Shuohang Wang Lijuan Wang Chenguang Zhu Pengchuan Zhang Lu Yuan Nanyun Peng et al. 2022. An empirical study of training end-to-end vision-and-language transformers. In CVPR.","DOI":"10.1109\/CVPR52688.2022.01763"},{"key":"e_1_3_2_2_8_1","unstructured":"Zhiwei Hu V\u00edctor Guti\u00e9rrez-Basulto Ru Li and Jeff Z Pan. 2024. Multi-level Matching Network for Multimodal Entity Linking. In KDD."},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"crossref","unstructured":"Juyeon Kim Geon Lee Taeuk Kim and Kijung Shin. 2025. Code datasets and online appendix of the paper ''KGMEL: Knowledge Graph-Enhanced Multimodal Entity Linking''. https:\/\/github.com\/juyeonnn\/KGMEL","DOI":"10.1145\/3726302.3730217"},{"key":"e_1_3_2_2_10_1","volume-title":"Vilt: Vision-and-language transformer without convolution or region supervision. In ICML.","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."},{"key":"e_1_3_2_2_11_1","unstructured":"Junnan Li Ramprasaath Selvaraju Akhilesh Gotmare Shafiq Joty Caiming Xiong and Steven Chu Hong Hoi. 2021. Align before fuse: Vision and language representation learning with momentum distillation. In NeurIPS."},{"key":"e_1_3_2_2_12_1","volume-title":"Zheng Zhang, Minlie Huang, and Tat-Seng Chua.","author":"Liao Lizi","year":"2021","unstructured":"Lizi Liao, Le Hong Long, Zheng Zhang, Minlie Huang, and Tat-Seng Chua. 2021. MMConv: an environment for multimodal conversational search across multiple domains. In SIGIR."},{"key":"e_1_3_2_2_13_1","unstructured":"Haotian Liu Chunyuan Li Qingyang Wu and Yong Jae Lee. 2024b. Visual instruction tuning. In NeurIPS."},{"key":"e_1_3_2_2_14_1","volume-title":"Unimel: A unified framework for multimodal entity linking with large language models. In CIKM.","author":"Liu Qi","year":"2024","unstructured":"Qi Liu, Yongyi He, Tong Xu, Defu Lian, Che Liu, Zhi Zheng, and Enhong Chen. 2024a. Unimel: A unified framework for multimodal entity linking with large language models. In CIKM."},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"crossref","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 Findings.","DOI":"10.18653\/v1\/2024.findings-acl.450"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"crossref","unstructured":"Shayne Longpre Kartik Perisetla Anthony Chen Nikhil Ramesh Chris DuBois and Sameer Singh. 2021. Entity-Based Knowledge Conflicts in Question Answering. In EMNLP.","DOI":"10.18653\/v1\/2021.emnlp-main.565"},{"key":"e_1_3_2_2_17_1","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."},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"crossref","unstructured":"Edgar Meij Krisztian Balog and Daan Odijk. 2014. Entity linking and retrieval for semantic search. In WSDM.","DOI":"10.1145\/2556195.2556201"},{"key":"e_1_3_2_2_19_1","unstructured":"Hongze Mi Jinyuan Li Xuying Zhang Haoran Cheng Jiahao Wang Di Sun and Gang Pan. 2024. VP-MEL: Visual Prompts Guided Multimodal Entity Linking."},{"key":"e_1_3_2_2_20_1","unstructured":"Seungwhan Moon Leonardo Neves and Vitor Carvalho. 2018. Multimodal named entity recognition for short social media posts. In ACL."},{"key":"e_1_3_2_2_21_1","unstructured":"OpenAI. 2023. GPT-3.5 Turbo. https:\/\/openai.com\/index\/gpt-3-5-turbo-fine-tuning-and-api-updates\/"},{"key":"e_1_3_2_2_22_1","unstructured":"OpenAI. 2024. GPT-4o mini: advancing cost-efficient intelligence. https:\/\/openai.com\/index\/gpt-4o-mini-advancing-cost-efficient-intelligence\/"},{"key":"e_1_3_2_2_23_1","volume-title":"Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al.","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, et al., 2021. Learning transferable visual models from natural language supervision. In ICML."},{"key":"e_1_3_2_2_24_1","unstructured":"Senbao Shi Zhenran Xu Baotian Hu and Min Zhang. 2024. Generative multimodal entity linking. In LREC-COLING."},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"crossref","unstructured":"Shezheng Song Shan Zhao Chengyu Wang Tianwei Yan Shasha Li Xiaoguang Mao and Meng Wang. 2024. A dual-way enhanced framework from text matching point of view for multimodal entity linking. In AAAI.","DOI":"10.1609\/aaai.v38i17.29867"},{"key":"e_1_3_2_2_26_1","volume-title":"MELOV: Multimodal entity linking with optimized visual features in latent space. In Findings of ACL.","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 Findings of ACL."},{"key":"e_1_3_2_2_27_1","volume-title":"Visualizing data using t-SNE","author":"der Maaten Laurens Van","year":"2008","unstructured":"Laurens Van der Maaten and Geoffrey Hinton. 2008. Visualizing data using t-SNE. Vol. 9, 11 (2008)."},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"crossref","unstructured":"Peng Wang Jiangheng Wu and Xiaohang Chen. 2022b. Multimodal entity linking with gated hierarchical fusion and contrastive training. In SIGIR.","DOI":"10.1145\/3477495.3531867"},{"key":"e_1_3_2_2_29_1","volume-title":"Henry Zhu, Sheng Zhang, Chung-Wei Hang, Pramuditha Perera, Jie Ma, William Wang, Zhiguo Wang, Vittorio Castelli, et al.","author":"Wang Sijia","year":"2023","unstructured":"Sijia Wang, Alexander Hanbo Li, Henry Zhu, Sheng Zhang, Chung-Wei Hang, Pramuditha Perera, Jie Ma, William Wang, Zhiguo Wang, Vittorio Castelli, et al., 2023. Benchmarking diverse-modal entity linking with generative models. In ACL Findings."},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"crossref","unstructured":"Xuwu Wang Junfeng Tian Min Gui Zhixu Li Rui Wang Ming Yan Lihan Chen and Yanghua Xiao. 2022a. WikiDiverse: a multimodal entity linking dataset with diversified contextual topics and entity types. In ACL.","DOI":"10.18653\/v1\/2022.acl-long.328"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"crossref","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.","DOI":"10.18653\/v1\/P19-1417"},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"crossref","unstructured":"Zefeng Zhang Jiawei Sheng Chuang Zhang Yunzhi Liang Wenyuan Zhang Siqi Wang and Tingwen Liu. 2024. Optimal Transport Guided Correlation Assignment for Multimodal Entity Linking. In Findings of ACL.","DOI":"10.18653\/v1\/2024.findings-acl.243"},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1162\/dint_a_00114"}],"event":{"name":"SIGIR '25: The 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","location":"Padua Italy","acronym":"SIGIR '25","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3726302.3730217","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T12:09:15Z","timestamp":1755864555000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3726302.3730217"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,13]]},"references-count":33,"alternative-id":["10.1145\/3726302.3730217","10.1145\/3726302"],"URL":"https:\/\/doi.org\/10.1145\/3726302.3730217","relation":{},"subject":[],"published":{"date-parts":[[2025,7,13]]},"assertion":[{"value":"2025-07-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}