{"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/neural-related-work-summarization-with-a","title":"Neural Related Work Summarization with a Joint Context-driven Attention Mechanism","arxiv_id":"1901.09492","date":"2019-01-28","proceeding":"EMNLP 2018 10","authors":["Yongzhen Wang","Xiaozhong Liu","Zheng Gao"],"abstract":"Conventional solutions to automatic related work summarization rely heavily\non human-engineered features. In this paper, we develop a neural data-driven\nsummarizer by leveraging the seq2seq paradigm, in which a joint context-driven\nattention mechanism is proposed to measure the contextual relevance within full\ntexts and a heterogeneous bibliography graph simultaneously. Our motivation is\nto maintain the topic coherency between a related work section and its target\ndocument, where both the textual and graphic contexts play a big role in\ncharacterizing the relationship among scientific publications accurately.\nExperimental results on a large dataset show that our approach achieves a\nconsiderable improvement over a typical seq2seq summarizer and five classical\nsummarization baselines.","url_abs":"http://arxiv.org/abs/1901.09492v1","url_pdf":"http://arxiv.org/pdf/1901.09492v1.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":"neural-related-work-summarization-with-a","repo_url":"https://github.com/kuadmu/2018EMNLP","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[],"methods":[{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"seq2seq","method_name":"Seq2Seq"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1901.09492","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}