{"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/triad-based-neural-network-for-coreference","title":"Triad-based Neural Network for Coreference Resolution","arxiv_id":"1809.06491","date":"2018-09-18","proceeding":"COLING 2018 8","authors":["Yuanliang Meng","Anna Rumshisky"],"abstract":"We propose a triad-based neural network system that generates affinity scores\nbetween entity mentions for coreference resolution. The system simultaneously\naccepts three mentions as input, taking mutual dependency and logical\nconstraints of all three mentions into account, and thus makes more accurate\npredictions than the traditional pairwise approach. Depending on system\nchoices, the affinity scores can be further used in clustering or mention\nranking. Our experiments show that a standard hierarchical clustering using the\nscores produces state-of-art results with gold mentions on the English portion\nof CoNLL 2012 Shared Task. The model does not rely on many handcrafted features\nand is easy to train and use. The triads can also be easily extended to polyads\nof higher orders. To our knowledge, this is the first neural network system to\nmodel mutual dependency of more than two members at mention level.","url_abs":"http://arxiv.org/abs/1809.06491v1","url_pdf":"http://arxiv.org/pdf/1809.06491v1.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":"triad-based-neural-network-for-coreference","repo_url":"https://github.com/text-machine-lab/entity-coref","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"clustering","task_name":"Clustering"},{"task_slug":"coreference-resolution","task_name":"Coreference Resolution"},{"task_slug":"coreference-resolution-1","task_name":"coreference-resolution"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}