{"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/entity-tracking-improves-cloze-style-reading","title":"Entity Tracking Improves Cloze-style Reading Comprehension","arxiv_id":"1810.02891","date":"2018-10-05","proceeding":"EMNLP 2018 10","authors":["Luong Hoang","Sam Wiseman","Alexander M. Rush"],"abstract":"Reading comprehension tasks test the ability of models to process long-term\ncontext and remember salient information. Recent work has shown that relatively\nsimple neural methods such as the Attention Sum-Reader can perform well on\nthese tasks; however, these systems still significantly trail human\nperformance. Analysis suggests that many of the remaining hard instances are\nrelated to the inability to track entity-references throughout documents. This\nwork focuses on these hard entity tracking cases with two extensions: (1)\nadditional entity features, and (2) training with a multi-task tracking\nobjective. We show that these simple modifications improve performance both\nindependently and in combination, and we outperform the previous state of the\nart on the LAMBADA dataset, particularly on difficult entity examples.","url_abs":"http://arxiv.org/abs/1810.02891v1","url_pdf":"http://arxiv.org/pdf/1810.02891v1.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":"entity-tracking-improves-cloze-style-reading","repo_url":"https://github.com/harvardnlp/readcomp","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"lambada","task_name":"LAMBADA"},{"task_slug":"reading-comprehension","task_name":"Reading Comprehension"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1810.02891","atlas_url":"https://app.syntology.ai/?focus=1810.02891","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}