{"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-communicating-agents-for-abstractive","title":"Deep Communicating Agents for Abstractive Summarization","arxiv_id":"1803.10357","date":"2018-03-27","proceeding":"NAACL 2018 6","authors":["Asli Celikyilmaz","Antoine Bosselut","Xiaodong He","Yejin Choi"],"abstract":"We present deep communicating agents in an encoder-decoder architecture to\naddress the challenges of representing a long document for abstractive\nsummarization. With deep communicating agents, the task of encoding a long text\nis divided across multiple collaborating agents, each in charge of a subsection\nof the input text. These encoders are connected to a single decoder, trained\nend-to-end using reinforcement learning to generate a focused and coherent\nsummary. Empirical results demonstrate that multiple communicating encoders\nlead to a higher quality summary compared to several strong baselines,\nincluding those based on a single encoder or multiple non-communicating\nencoders.","url_abs":"http://arxiv.org/abs/1803.10357v3","url_pdf":"http://arxiv.org/pdf/1803.10357v3.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":"abstractive-text-summarization","task_name":"Abstractive Text Summarization"},{"task_slug":"decoder","task_name":"Decoder"},{"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":[{"leaderboard":"/sota/abstractive-text-summarization-on-cnn-daily","task":"Abstractive Text Summarization","dataset":"CNN / Daily Mail","model":"DCA","rank_in_archive_order":31,"of":53,"metrics":{"ROUGE-1":"41.69","ROUGE-2":"19.47","ROUGE-L":"37.92"},"uses_additional_data":true}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1803.10357","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}