{"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/stance-detection-with-bidirectional","title":"Stance Detection with Bidirectional Conditional Encoding","arxiv_id":"1606.05464","date":"2016-06-17","proceeding":"EMNLP 2016 11","authors":["Isabelle Augenstein","Tim Rocktäschel","Andreas Vlachos","Kalina Bontcheva"],"abstract":"Stance detection is the task of classifying the attitude expressed in a text\ntowards a target such as Hillary Clinton to be \"positive\", negative\" or\n\"neutral\". Previous work has assumed that either the target is mentioned in the\ntext or that training data for every target is given. This paper considers the\nmore challenging version of this task, where targets are not always mentioned\nand no training data is available for the test targets. We experiment with\nconditional LSTM encoding, which builds a representation of the tweet that is\ndependent on the target, and demonstrate that it outperforms encoding the tweet\nand the target independently. Performance is improved further when the\nconditional model is augmented with bidirectional encoding. We evaluate our\napproach on the SemEval 2016 Task 6 Twitter Stance Detection corpus achieving\nperformance second best only to a system trained on semi-automatically labelled\ntweets for the test target. When such weak supervision is added, our approach\nachieves state-of-the-art results.","url_abs":"http://arxiv.org/abs/1606.05464v2","url_pdf":"http://arxiv.org/pdf/1606.05464v2.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":"stance-detection-with-bidirectional","repo_url":"https://github.com/sheffieldnlp/stance-conditional","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"stance-detection","task_name":"Stance Detection"}],"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=1606.05464","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}