{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/focus-on-what-matters-applying-discourse","title":"Focus on what matters: Applying Discourse Coherence Theory to Cross Document Coreference","arxiv_id":"2110.05362","date":"2021-10-11","proceeding":"EMNLP 2021 11","authors":["William Held","Dan Iter","Dan Jurafsky"],"abstract":"Performing event and entity coreference resolution across documents vastly increases the number of candidate mentions, making it intractable to do the full $n^2$ pairwise comparisons. Existing approaches simplify by considering coreference only within document clusters, but this fails to handle inter-cluster coreference, common in many applications. As a result cross-document coreference algorithms are rarely applied to downstream tasks. We draw on an insight from discourse coherence theory: potential coreferences are constrained by the reader's discourse focus. We model the entities/events in a reader's focus as a neighborhood within a learned latent embedding space which minimizes the distance between mentions and the centroids of their gold coreference clusters. We then use these neighborhoods to sample only hard negatives to train a fine-grained classifier on mention pairs and their local discourse features. Our approach achieves state-of-the-art results for both events and entities on the ECB+, Gun Violence, Football Coreference, and Cross-Domain Cross-Document Coreference corpora. Furthermore, training on multiple corpora improves average performance across all datasets by 17.2 F1 points, leading to a robust coreference resolution model for use in downstream tasks where link distribution is unknown.","url_abs":"https://arxiv.org/abs/2110.05362v1","url_pdf":"https://arxiv.org/pdf/2110.05362v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"focus-on-what-matters-applying-discourse","repo_url":"https://github.com/helw150/event_entity_coref_ecb_plus","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"coreference-resolution","task_name":"Coreference Resolution"},{"task_slug":"entity-cross-document-coreference-resolution","task_name":"Entity Cross-Document Coreference Resolution"},{"task_slug":"event-coreference-resolution","task_name":"Event Coreference Resolution"},{"task_slug":"event-cross-document-coreference-resolution","task_name":"Event Cross-Document Coreference Resolution"},{"task_slug":"coreference-resolution-1","task_name":"coreference-resolution"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2110.05362","atlas_url":"https://app.syntology.ai/?focus=2110.05362","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}