{"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/a-multi-level-attention-model-for-evidence","title":"A Multi-Level Attention Model for Evidence-Based Fact Checking","arxiv_id":"2106.00950","date":"2021-06-02","proceeding":"Findings (ACL) 2021 8","authors":["Canasai Kruengkrai","Junichi Yamagishi","Xin Wang"],"abstract":"Evidence-based fact checking aims to verify the truthfulness of a claim against evidence extracted from textual sources. Learning a representation that effectively captures relations between a claim and evidence can be challenging. Recent state-of-the-art approaches have developed increasingly sophisticated models based on graph structures. We present a simple model that can be trained on sequence structures. Our model enables inter-sentence attentions at different levels and can benefit from joint training. Results on a large-scale dataset for Fact Extraction and VERification (FEVER) show that our model outperforms the graph-based approaches and yields 1.09% and 1.42% improvements in label accuracy and FEVER score, respectively, over the best published model.","url_abs":"https://arxiv.org/abs/2106.00950v1","url_pdf":"https://arxiv.org/pdf/2106.00950v1.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":"a-multi-level-attention-model-for-evidence","repo_url":"https://github.com/nii-yamagishilab/mla","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"a-multi-level-attention-model-for-evidence","repo_url":"https://github.com/ZIZUN/MAFiD","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"fact-checking","task_name":"Fact Checking"},{"task_slug":"sentence","task_name":"Sentence"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2106.00950","atlas_url":"https://app.syntology.ai/?focus=2106.00950","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}