{"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/left-center-right-separated-neural-network","title":"Left-Center-Right Separated Neural Network for Aspect-based Sentiment Analysis with Rotatory Attention","arxiv_id":"1802.00892","date":"2018-02-03","proceeding":null,"authors":["Shiliang Zheng","Rui Xia"],"abstract":"Deep learning techniques have achieved success in aspect-based sentiment\nanalysis in recent years. However, there are two important issues that still\nremain to be further studied, i.e., 1) how to efficiently represent the target\nespecially when the target contains multiple words; 2) how to utilize the\ninteraction between target and left/right contexts to capture the most\nimportant words in them. In this paper, we propose an approach, called\nleft-center-right separated neural network with rotatory attention (LCR-Rot),\nto better address the two problems. Our approach has two characteristics: 1) it\nhas three separated LSTMs, i.e., left, center and right LSTMs, corresponding to\nthree parts of a review (left context, target phrase and right context); 2) it\nhas a rotatory attention mechanism which models the relation between target and\nleft/right contexts. The target2context attention is used to capture the most\nindicative sentiment words in left/right contexts. Subsequently, the\ncontext2target attention is used to capture the most important word in the\ntarget. This leads to a two-side representation of the target: left-aware\ntarget and right-aware target. We compare our approach on three benchmark\ndatasets with ten related methods proposed recently. The results show that our\napproach significantly outperforms the state-of-the-art techniques.","url_abs":"http://arxiv.org/abs/1802.00892v1","url_pdf":"http://arxiv.org/pdf/1802.00892v1.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":"left-center-right-separated-neural-network","repo_url":"https://github.com/NUSTM/ABSC","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}}],"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","task":"Aspect-Based Sentiment Analysis (ABSA)","dataset":"SemEval-2014 Task-4","model":"LCR-Rot","rank_in_archive_order":27,"of":48,"metrics":{"Laptop (Acc)":"75.24","Mean Acc (Restaurant + Laptop)":"78.29","Restaurant (Acc)":"81.34"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1802.00892","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}