{"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/knowledge-enhanced-masked-language-model-for","title":"Knowledge Enhanced Masked Language Model for Stance Detection","arxiv_id":null,"date":"2021-05-26","proceeding":"NAACL 2021 4","authors":["Kornraphop Kawintiranon","Lisa Singh"],"abstract":"Detecting stance on Twitter is especially challenging because of the short length of each tweet, the continuous coinage of new terminology and hashtags, and the deviation of sentence structure from standard prose. Fine-tuned language models using large-scale in-domain data have been shown to be the new state-of-the-art for many NLP tasks, including stance detection. In this paper, we propose a novel BERT-based fine-tuning method that enhances the masked language model for stance detection. Instead of random token masking, we propose using a weighted log-odds-ratio to identify words with high stance distinguishability and then model an attention mechanism that focuses on these words. We show that our proposed approach outperforms the state of the art for stance detection on Twitter data about the 2020 US Presidential election.","url_abs":"https://aclanthology.org/2021.naacl-main.376","url_pdf":"https://aclanthology.org/2021.naacl-main.376.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":"knowledge-enhanced-masked-language-model-for","repo_url":"https://github.com/GU-DataLab/stance-detection-KE-MLM","is_official":0,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"stance-detection","task_name":"Stance Detection"},{"task_slug":"stance-detection-us-election-2020-biden","task_name":"Stance Detection (US Election 2020 - Biden)"},{"task_slug":"stance-detection-us-election-2020-trump","task_name":"Stance Detection (US Election 2020 - Trump)"}],"methods":[{"method_slug":"ke-mlm","method_name":"KE-MLM"}],"datasets_introduced":[{"slug":"twitter-stance-election-2020","name":"Twitter Stance Election 2020","full_name":""}],"methods_introduced":[{"slug":"ke-mlm","name":"KE-MLM","full_name":"Knowledge Enhanced Masked Language Model"}],"results":[{"leaderboard":"/sota/stance-detection-us-election-2020-biden-on","task":"Stance Detection (US Election 2020 - Biden)","dataset":"Twitter Stance Election 2020","model":"KE-MLM","rank_in_archive_order":1,"of":1,"metrics":{"Average F1":"0.7577"},"uses_additional_data":true},{"leaderboard":"/sota/stance-detection-us-election-2020-trump-on","task":"Stance Detection (US Election 2020 - Trump)","dataset":"Twitter Stance Election 2020","model":"KE-MLM","rank_in_archive_order":1,"of":1,"metrics":{"Average F1":"0.7877"},"uses_additional_data":true}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}