{"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/exploiting-document-knowledge-for-aspect","title":"Exploiting Document Knowledge for Aspect-level Sentiment Classification","arxiv_id":"1806.04346","date":"2018-06-12","proceeding":"ACL 2018 7","authors":["Ruidan He","Wee Sun Lee","Hwee Tou Ng","Daniel Dahlmeier"],"abstract":"Attention-based long short-term memory (LSTM) networks have proven to be\nuseful in aspect-level sentiment classification. However, due to the\ndifficulties in annotating aspect-level data, existing public datasets for this\ntask are all relatively small, which largely limits the effectiveness of those\nneural models. In this paper, we explore two approaches that transfer knowledge\nfrom document- level data, which is much less expensive to obtain, to improve\nthe performance of aspect-level sentiment classification. We demonstrate the\neffectiveness of our approaches on 4 public datasets from SemEval 2014, 2015,\nand 2016, and we show that attention-based LSTM benefits from document-level\nknowledge in multiple ways.","url_abs":"http://arxiv.org/abs/1806.04346v1","url_pdf":"http://arxiv.org/pdf/1806.04346v1.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":"exploiting-document-knowledge-for-aspect","repo_url":"https://github.com/ruidan/Aspect-level-sentiment","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null}],"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":"sentiment-analysis","task_name":"Sentiment Analysis"},{"task_slug":"sentiment-classification","task_name":"Sentiment Classification"}],"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":[{"leaderboard":"/sota/aspect-based-sentiment-analysis-on-semeval","task":"Aspect-Based Sentiment Analysis (ABSA)","dataset":"SemEval-2014 Task-4","model":"PRET+MULT","rank_in_archive_order":39,"of":48,"metrics":{"Laptop (Acc)":"71.15","Mean Acc (Restaurant + Laptop)":"75.13","Restaurant (Acc)":"79.11"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1806.04346","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}