{"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/generative-adversarial-network-for","title":"Generative Adversarial Network for Abstractive Text Summarization","arxiv_id":"1711.09357","date":"2017-11-26","proceeding":null,"authors":["Linqing Liu","Yao Lu","Min Yang","Qiang Qu","Jia Zhu","Hongyan Li"],"abstract":"In this paper, we propose an adversarial process for abstractive text\nsummarization, in which we simultaneously train a generative model G and a\ndiscriminative model D. In particular, we build the generator G as an agent of\nreinforcement learning, which takes the raw text as input and predicts the\nabstractive summarization. We also build a discriminator which attempts to\ndistinguish the generated summary from the ground truth summary. Extensive\nexperiments demonstrate that our model achieves competitive ROUGE scores with\nthe state-of-the-art methods on CNN/Daily Mail dataset. Qualitatively, we show\nthat our model is able to generate more abstractive, readable and diverse\nsummaries.","url_abs":"http://arxiv.org/abs/1711.09357v1","url_pdf":"http://arxiv.org/pdf/1711.09357v1.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":"generative-adversarial-network-for","repo_url":"https://github.com/iwangjian/textsum-gan","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"abstractive-text-summarization","task_name":"Abstractive Text Summarization"},{"task_slug":null,"task_name":"Generative Adversarial Network"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"text-summarization","task_name":"Text Summarization"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/text-summarization-on-cnn-daily-mail-2","task":"Text Summarization","dataset":"CNN / Daily Mail (Anonymized)","model":"GAN","rank_in_archive_order":5,"of":13,"metrics":{"ROUGE-1":"39.92","ROUGE-2":"17.65","ROUGE-L":"36.71"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1711.09357","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}