{"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/aspect-based-sentiment-analysis-with-gated","title":"Aspect Based Sentiment Analysis with Gated Convolutional Networks","arxiv_id":"1805.07043","date":"2018-05-18","proceeding":"ACL 2018 7","authors":["Wei Xue","Tao Li"],"abstract":"Aspect based sentiment analysis (ABSA) can provide more detailed information\nthan general sentiment analysis, because it aims to predict the sentiment\npolarities of the given aspects or entities in text. We summarize previous\napproaches into two subtasks: aspect-category sentiment analysis (ACSA) and\naspect-term sentiment analysis (ATSA). Most previous approaches employ long\nshort-term memory and attention mechanisms to predict the sentiment polarity of\nthe concerned targets, which are often complicated and need more training time.\nWe propose a model based on convolutional neural networks and gating\nmechanisms, which is more accurate and efficient. First, the novel Gated\nTanh-ReLU Units can selectively output the sentiment features according to the\ngiven aspect or entity. The architecture is much simpler than attention layer\nused in the existing models. Second, the computations of our model could be\neasily parallelized during training, because convolutional layers do not have\ntime dependency as in LSTM layers, and gating units also work independently.\nThe experiments on SemEval datasets demonstrate the efficiency and\neffectiveness of our models.","url_abs":"http://arxiv.org/abs/1805.07043v1","url_pdf":"http://arxiv.org/pdf/1805.07043v1.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":"aspect-based-sentiment-analysis-with-gated","repo_url":"https://github.com/wxue004cs/GCAE","is_official":0,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"aspect-category-sentiment-analysis","task_name":"Aspect Category Sentiment Analysis"},{"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":[{"method_slug":"lstm","method_name":"LSTM"},{"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=1805.07043","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}