{"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/towards-the-use-of-deep-reinforcement","title":"Towards the Use of Deep Reinforcement Learning with Global Policy For Query-based Extractive Summarisation","arxiv_id":"1711.03859","date":"2017-11-10","proceeding":null,"authors":["Diego Molla"],"abstract":"Supervised approaches for text summarisation suffer from the problem of\nmismatch between the target labels/scores of individual sentences and the\nevaluation score of the final summary. Reinforcement learning can solve this\nproblem by providing a learning mechanism that uses the score of the final\nsummary as a guide to determine the decisions made at the time of selection of\neach sentence. In this paper we present a proof-of-concept approach that\napplies a policy-gradient algorithm to learn a stochastic policy using an\nundiscounted reward. The method has been applied to a policy consisting of a\nsimple neural network and simple features. The resulting deep reinforcement\nlearning system is able to learn a global policy and obtain encouraging\nresults.","url_abs":"http://arxiv.org/abs/1711.03859v2","url_pdf":"http://arxiv.org/pdf/1711.03859v2.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":"towards-the-use-of-deep-reinforcement","repo_url":"https://github.com/dmollaaliod/alta2017-rl","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"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":"sentence","task_name":"Sentence"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"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}