{"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/diversity-driven-attention-model-for-query","title":"Diversity driven Attention Model for Query-based Abstractive Summarization","arxiv_id":"1704.08300","date":"2017-04-26","proceeding":"ACL 2017 7","authors":["Preksha Nema","Mitesh Khapra","Anirban Laha","Balaraman Ravindran"],"abstract":"Abstractive summarization aims to generate a shorter version of the document\ncovering all the salient points in a compact and coherent fashion. On the other\nhand, query-based summarization highlights those points that are relevant in\nthe context of a given query. The encode-attend-decode paradigm has achieved\nnotable success in machine translation, extractive summarization, dialog\nsystems, etc. But it suffers from the drawback of generation of repeated\nphrases. In this work we propose a model for the query-based summarization task\nbased on the encode-attend-decode paradigm with two key additions (i) a query\nattention model (in addition to document attention model) which learns to focus\non different portions of the query at different time steps (instead of using a\nstatic representation for the query) and (ii) a new diversity based attention\nmodel which aims to alleviate the problem of repeating phrases in the summary.\nIn order to enable the testing of this model we introduce a new query-based\nsummarization dataset building on debatepedia. Our experiments show that with\nthese two additions the proposed model clearly outperforms vanilla\nencode-attend-decode models with a gain of 28% (absolute) in ROUGE-L scores.","url_abs":"http://arxiv.org/abs/1704.08300v2","url_pdf":"http://arxiv.org/pdf/1704.08300v2.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":"diversity-driven-attention-model-for-query","repo_url":"https://github.com/PrekshaNema25/DiverstiyBasedAttentionMechanism","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"diversity-driven-attention-model-for-query","repo_url":"https://github.com/maheshmylavarapu0057/QueryBasedSummarisation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"abstractive-text-summarization","task_name":"Abstractive Text Summarization"},{"task_slug":"diversity","task_name":"Diversity"},{"task_slug":"extractive-summarization","task_name":"Extractive Summarization"},{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"query-based-extractive-summarization","task_name":"Query-Based Extractive Summarization"},{"task_slug":"translation","task_name":"Translation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/query-based-extractive-summarization-on","task":"Query-Based Extractive Summarization","dataset":"Debatepedia","model":"SD2","rank_in_archive_order":2,"of":2,"metrics":{"ROUGE-1":"41.26"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1704.08300","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}