{"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/twowingos-a-two-wing-optimization-strategy","title":"TwoWingOS: A Two-Wing Optimization Strategy for Evidential Claim Verification","arxiv_id":"1808.03465","date":"2018-08-10","proceeding":"EMNLP 2018 10","authors":["Wenpeng Yin","Dan Roth"],"abstract":"Determining whether a given claim is supported by evidence is a fundamental\nNLP problem that is best modeled as Textual Entailment. However, given a large\ncollection of text, finding evidence that could support or refute a given claim\nis a challenge in itself, amplified by the fact that different evidence might\nbe needed to support or refute a claim. Nevertheless, most prior work decouples\nevidence identification from determining the truth value of the claim given the\nevidence.\n  We propose to consider these two aspects jointly. We develop TwoWingOS\n(two-wing optimization strategy), a system that, while identifying appropriate\nevidence for a claim, also determines whether or not the claim is supported by\nthe evidence. Given the claim, TwoWingOS attempts to identify a subset of the\nevidence candidates; given the predicted evidence, it then attempts to\ndetermine the truth value of the corresponding claim. We treat this challenge\nas coupled optimization problems, training a joint model for it. TwoWingOS\noffers two advantages: (i) Unlike pipeline systems, it facilitates\nflexible-size evidence set, and (ii) Joint training improves both the claim\nentailment and the evidence identification. Experiments on a benchmark dataset\nshow state-of-the-art performance. Code: https://github.com/yinwenpeng/FEVER","url_abs":"http://arxiv.org/abs/1808.03465v2","url_pdf":"http://arxiv.org/pdf/1808.03465v2.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":"twowingos-a-two-wing-optimization-strategy","repo_url":"https://github.com/yinwenpeng/FEVER","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"claim-verification","task_name":"Claim Verification"},{"task_slug":"natural-language-inference","task_name":"Natural Language Inference"},{"task_slug":"two","task_name":"Vocal Bursts Valence Prediction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1808.03465","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}