{"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/selective-encoding-for-abstractive-sentence","title":"Selective Encoding for Abstractive Sentence Summarization","arxiv_id":"1704.07073","date":"2017-04-24","proceeding":"ACL 2017 7","authors":["Qingyu Zhou","Nan Yang","Furu Wei","Ming Zhou"],"abstract":"We propose a selective encoding model to extend the sequence-to-sequence\nframework for abstractive sentence summarization. It consists of a sentence\nencoder, a selective gate network, and an attention equipped decoder. The\nsentence encoder and decoder are built with recurrent neural networks. The\nselective gate network constructs a second level sentence representation by\ncontrolling the information flow from encoder to decoder. The second level\nrepresentation is tailored for sentence summarization task, which leads to\nbetter performance. We evaluate our model on the English Gigaword, DUC 2004 and\nMSR abstractive sentence summarization datasets. The experimental results show\nthat the proposed selective encoding model outperforms the state-of-the-art\nbaseline models.","url_abs":"http://arxiv.org/abs/1704.07073v1","url_pdf":"http://arxiv.org/pdf/1704.07073v1.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":"selective-encoding-for-abstractive-sentence","repo_url":"https://github.com/magic282/SEASS","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"selective-encoding-for-abstractive-sentence","repo_url":"https://github.com/toru34/zhou_acl_2017","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"sentence-summarization","task_name":"Sentence Summarization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/text-summarization-on-duc-2004-task-1","task":"Text Summarization","dataset":"DUC 2004 Task 1","model":"SEASS","rank_in_archive_order":8,"of":13,"metrics":{"ROUGE-1":"29.21","ROUGE-2":"9.56","ROUGE-L":"25.51"},"uses_additional_data":false},{"leaderboard":"/sota/text-summarization-on-gigaword","task":"Text Summarization","dataset":"GigaWord","model":"SEASS","rank_in_archive_order":34,"of":41,"metrics":{"ROUGE-1":"36.15","ROUGE-2":"17.54","ROUGE-L":"33.63"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1704.07073","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}