{"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/abstractive-summarization-using-attentive","title":"Abstractive Summarization Using Attentive Neural Techniques","arxiv_id":"1810.08838","date":"2018-10-20","proceeding":null,"authors":["Jacob Krantz","Jugal Kalita"],"abstract":"In a world of proliferating data, the ability to rapidly summarize text is\ngrowing in importance. Automatic summarization of text can be thought of as a\nsequence to sequence problem. Another area of natural language processing that\nsolves a sequence to sequence problem is machine translation, which is rapidly\nevolving due to the development of attention-based encoder-decoder networks.\nThis work applies these modern techniques to abstractive summarization. We\nperform analysis on various attention mechanisms for summarization with the\ngoal of developing an approach and architecture aimed at improving the state of\nthe art. In particular, we modify and optimize a translation model with\nself-attention for generating abstractive sentence summaries. The effectiveness\nof this base model along with attention variants is compared and analyzed in\nthe context of standardized evaluation sets and test metrics. However, we show\nthat these metrics are limited in their ability to effectively score\nabstractive summaries, and propose a new approach based on the intuition that\nan abstractive model requires an abstractive evaluation.","url_abs":"http://arxiv.org/abs/1810.08838v1","url_pdf":"http://arxiv.org/pdf/1810.08838v1.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":"abstractive-summarization-using-attentive","repo_url":"https://github.com/jacobkrantz/VertMetric","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"abstractive-summarization-using-attentive","repo_url":"https://github.com/jacobkrantz/NeuralSum","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"abstractive-text-summarization","task_name":"Abstractive Text Summarization"},{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"translation","task_name":"Translation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}