{"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/recurrent-entity-networks-with-delayed-memory","title":"Recurrent Entity Networks with Delayed Memory Update for Targeted Aspect-based Sentiment Analysis","arxiv_id":"1804.11019","date":"2018-04-30","proceeding":"NAACL 2018 6","authors":["Fei Liu","Trevor Cohn","Timothy Baldwin"],"abstract":"While neural networks have been shown to achieve impressive results for\nsentence-level sentiment analysis, targeted aspect-based sentiment analysis\n(TABSA) --- extraction of fine-grained opinion polarity w.r.t. a pre-defined\nset of aspects --- remains a difficult task. Motivated by recent advances in\nmemory-augmented models for machine reading, we propose a novel architecture,\nutilising external \"memory chains\" with a delayed memory update mechanism to\ntrack entities. On a TABSA task, the proposed model demonstrates substantial\nimprovements over state-of-the-art approaches, including those using external\nknowledge bases.","url_abs":"http://arxiv.org/abs/1804.11019v1","url_pdf":"http://arxiv.org/pdf/1804.11019v1.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":"recurrent-entity-networks-with-delayed-memory","repo_url":"https://github.com/liufly/delayed-memory-update-entnet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"aspect-based-sentiment-analysis-1","task_name":"Aspect-Based Sentiment Analysis"},{"task_slug":"aspect-based-sentiment-analysis","task_name":"Aspect-Based Sentiment Analysis (ABSA)"},{"task_slug":"reading-comprehension","task_name":"Reading Comprehension"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"sentiment-analysis","task_name":"Sentiment Analysis"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/aspect-based-sentiment-analysis-on-sentihood","task":"Aspect-Based Sentiment Analysis (ABSA)","dataset":"Sentihood","model":"Liu et al.","rank_in_archive_order":3,"of":5,"metrics":{"Aspect":"78.5","Sentiment":"91.0"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1804.11019","atlas_url":"https://app.syntology.ai/?focus=1804.11019","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}