{"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/a-reinforced-topic-aware-convolutional","title":"A Reinforced Topic-Aware Convolutional Sequence-to-Sequence Model for Abstractive Text Summarization","arxiv_id":"1805.03616","date":"2018-05-09","proceeding":null,"authors":["Li Wang","Junlin Yao","Yunzhe Tao","Li Zhong","Wei Liu","Qiang Du"],"abstract":"In this paper, we propose a deep learning approach to tackle the automatic summarization tasks by incorporating topic information into the convolutional sequence-to-sequence (ConvS2S) model and using self-critical sequence training (SCST) for optimization. Through jointly attending to topics and word-level alignment, our approach can improve coherence, diversity, and informativeness of generated summaries via a biased probability generation mechanism. On the other hand, reinforcement training, like SCST, directly optimizes the proposed model with respect to the non-differentiable metric ROUGE, which also avoids the exposure bias during inference. We carry out the experimental evaluation with state-of-the-art methods over the Gigaword, DUC-2004, and LCSTS datasets. The empirical results demonstrate the superiority of our proposed method in the abstractive summarization.","url_abs":"https://arxiv.org/abs/1805.03616v3","url_pdf":"https://arxiv.org/pdf/1805.03616v3.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":"diversity","task_name":"Diversity"},{"task_slug":"informativeness","task_name":"Informativeness"},{"task_slug":"text-summarization","task_name":"Text Summarization"}],"methods":[{"method_slug":"scst","method_name":"SCST"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/text-summarization-on-duc-2004-task-1","task":"Text Summarization","dataset":"DUC 2004 Task 1","model":"Reinforced-Topic-ConvS2S","rank_in_archive_order":6,"of":13,"metrics":{"ROUGE-1":"31.15","ROUGE-2":"10.85","ROUGE-L":"27.68"},"uses_additional_data":false},{"leaderboard":"/sota/text-summarization-on-gigaword","task":"Text Summarization","dataset":"GigaWord","model":"Reinforced-Topic-ConvS2S","rank_in_archive_order":28,"of":41,"metrics":{"ROUGE-1":"36.92","ROUGE-2":"18.29","ROUGE-L":"34.58"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1805.03616","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}