{"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/recursive-neural-conditional-random-fields","title":"Recursive Neural Conditional Random Fields for Aspect-based Sentiment Analysis","arxiv_id":"1603.06679","date":"2016-03-22","proceeding":"EMNLP 2016 11","authors":["Wenya Wang","Sinno Jialin Pan","Daniel Dahlmeier","Xiaokui Xiao"],"abstract":"In aspect-based sentiment analysis, extracting aspect terms along with the\nopinions being expressed from user-generated content is one of the most\nimportant subtasks. Previous studies have shown that exploiting connections\nbetween aspect and opinion terms is promising for this task. In this paper, we\npropose a novel joint model that integrates recursive neural networks and\nconditional random fields into a unified framework for explicit aspect and\nopinion terms co-extraction. The proposed model learns high-level\ndiscriminative features and double propagate information between aspect and\nopinion terms, simultaneously. Moreover, it is flexible to incorporate\nhand-crafted features into the proposed model to further boost its information\nextraction performance. Experimental results on the SemEval Challenge 2014\ndataset show the superiority of our proposed model over several baseline\nmethods as well as the winning systems of the challenge.","url_abs":"http://arxiv.org/abs/1603.06679v3","url_pdf":"http://arxiv.org/pdf/1603.06679v3.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":[],"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":"sentiment-analysis","task_name":"Sentiment Analysis"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/aspect-based-sentiment-analysis-on-semeval-7","task":"Aspect-Based Sentiment Analysis (ABSA)","dataset":"SemEval 2014 Task 4 Sub Task 1","model":"RNCRF","rank_in_archive_order":4,"of":4,"metrics":{"Laptop (F1)":"78.42","Restaurant (F1)":"69.74"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1603.06679","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}