{"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/neural-models-for-reasoning-over-multiple","title":"Neural Models for Reasoning over Multiple Mentions using Coreference","arxiv_id":"1804.05922","date":"2018-04-16","proceeding":"NAACL 2018 6","authors":["Bhuwan Dhingra","Qiao Jin","Zhilin Yang","William W. Cohen","Ruslan Salakhutdinov"],"abstract":"Many problems in NLP require aggregating information from multiple mentions\nof the same entity which may be far apart in the text. Existing Recurrent\nNeural Network (RNN) layers are biased towards short-term dependencies and\nhence not suited to such tasks. We present a recurrent layer which is instead\nbiased towards coreferent dependencies. The layer uses coreference annotations\nextracted from an external system to connect entity mentions belonging to the\nsame cluster. Incorporating this layer into a state-of-the-art reading\ncomprehension model improves performance on three datasets -- Wikihop, LAMBADA\nand the bAbi AI tasks -- with large gains when training data is scarce.","url_abs":"http://arxiv.org/abs/1804.05922v1","url_pdf":"http://arxiv.org/pdf/1804.05922v1.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":[],"tasks":[{"task_slug":"lambada","task_name":"LAMBADA"},{"task_slug":"reading-comprehension","task_name":"Reading Comprehension"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/question-answering-on-wikihop","task":"Question Answering","dataset":"WikiHop","model":"Coref-GRU","rank_in_archive_order":7,"of":9,"metrics":{"Test":"59.3"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1804.05922","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}