{"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/transformation-networks-for-target-oriented","title":"Transformation Networks for Target-Oriented Sentiment Classification","arxiv_id":"1805.01086","date":"2018-05-03","proceeding":"ACL 2018 7","authors":["Xin Li","Lidong Bing","Wai Lam","Bei Shi"],"abstract":"Target-oriented sentiment classification aims at classifying sentiment\npolarities over individual opinion targets in a sentence. RNN with attention\nseems a good fit for the characteristics of this task, and indeed it achieves\nthe state-of-the-art performance. After re-examining the drawbacks of attention\nmechanism and the obstacles that block CNN to perform well in this\nclassification task, we propose a new model to overcome these issues. Instead\nof attention, our model employs a CNN layer to extract salient features from\nthe transformed word representations originated from a bi-directional RNN\nlayer. Between the two layers, we propose a component to generate\ntarget-specific representations of words in the sentence, meanwhile incorporate\na mechanism for preserving the original contextual information from the RNN\nlayer. Experiments show that our model achieves a new state-of-the-art\nperformance on a few benchmarks.","url_abs":"http://arxiv.org/abs/1805.01086v1","url_pdf":"http://arxiv.org/pdf/1805.01086v1.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":"transformation-networks-for-target-oriented","repo_url":"https://github.com/lixin4ever/TNet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"transformation-networks-for-target-oriented","repo_url":"https://github.com/mindspore-courses/ABSA-MindSpore","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"mindspore","reach":{"status":"gone","observed_at":"2026-09-17","how":"tree_404+repo_404"}}],"tasks":[{"task_slug":"aspect-based-sentiment-analysis","task_name":"Aspect-Based Sentiment Analysis (ABSA)"},{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"sentiment-classification","task_name":"Sentiment Classification"}],"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":"TNet-LF","rank_in_archive_order":24,"of":48,"metrics":{"Laptop (Acc)":"76.01","Mean Acc (Restaurant + Laptop)":"78.4","Restaurant (Acc)":"80.79"},"uses_additional_data":false},{"leaderboard":"/sota/aspect-based-sentiment-analysis-on-semeval","task":"Aspect-Based Sentiment Analysis (ABSA)","dataset":"SemEval-2014 Task-4","model":"TNet","rank_in_archive_order":47,"of":48,"metrics":{"Laptop (Acc)":"76.01","Restaurant (Acc)":"80.79"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1805.01086","atlas_url":"https://app.syntology.ai/?focus=1805.01086","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}