{"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/deep-reinforcement-learning-for-chinese-zero","title":"Deep Reinforcement Learning for Chinese Zero pronoun Resolution","arxiv_id":"1806.03711","date":"2018-06-10","proceeding":"ACL 2018 7","authors":["Qingyu Yin","Yu Zhang","Wei-Nan Zhang","Ting Liu","William Yang Wang"],"abstract":"Deep neural network models for Chinese zero pronoun resolution learn semantic\ninformation for zero pronoun and candidate antecedents, but tend to be\nshort-sighted---they often make local decisions. They typically predict\ncoreference chains between the zero pronoun and one single candidate antecedent\none link at a time, while overlooking their long-term influence on future\ndecisions. Ideally, modeling useful information of preceding potential\nantecedents is critical when later predicting zero pronoun-candidate antecedent\npairs. In this study, we show how to integrate local and global decision-making\nby exploiting deep reinforcement learning models. With the help of the\nreinforcement learning agent, our model learns the policy of selecting\nantecedents in a sequential manner, where useful information provided by\nearlier predicted antecedents could be utilized for making later coreference\ndecisions. Experimental results on OntoNotes 5.0 dataset show that our\ntechnique surpasses the state-of-the-art models.","url_abs":"http://arxiv.org/abs/1806.03711v2","url_pdf":"http://arxiv.org/pdf/1806.03711v2.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":"deep-reinforcement-learning-for-chinese-zero","repo_url":"https://github.com/qyyin/Reinforce4ZP","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"chinese-zero-pronoun-resolution","task_name":"Chinese Zero Pronoun Resolution"},{"task_slug":"decision-making","task_name":"Decision Making"},{"task_slug":"deep-reinforcement-learning","task_name":"Deep Reinforcement Learning"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1806.03711","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}