TwoWingOS: A Two-Wing Optimization Strategy for Evidential Claim Verification
Open accessThe DOI matches its Crossref record; 7 of the 7 references it cites were found in a registry or an index.
Abstract
Determining whether a given claim is supported by evidence is a fundamental NLP problem that is best modeled as Textual Entailment.However, given a large collection of text, finding evidence that could support or refute a given claim is a challenge in itself, amplified by the fact that different evidence might be needed to support or refute a claim.Nevertheless, most prior work decouples evidence identification from determining the truth value of the claim given the evidence.We propose to consider these two aspects jointly.We develop TWOWINGOS (twowing optimization strategy), a system that, while identifying appropriate evidence for a claim, also determines whether or not the claim is supported by the evidence.Given the claim, TWOWINGOS attempts to identify a subset of the evidence candidates; given the predicted evidence, it then attempts to determine the truth value of the corresponding claim.We treat this challenge as coupled optimization problems, training a joint model for it.TWOWINGOS offers two advantages: (i) Unlike pipeline systems, it facilitates flexible-size evidence set, and (ii) Joint training improves both the claim verification and the evidence identification.Experiments on a benchmark dataset show state-of-the-art performance.1
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Gradient-based learning applied to document recognition
Lecun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998) · Proceedings of the IEEE · doi:10.1109/5.726791 · Cited by 58,805
Freebase: a collaboratively created graph database for structuring human knowledge
Bollacker, K., Evans, C., Paritosh, P., Sturge, T., & Taylor, J. (2008) · Proceedings of the 2008 ACM SIGMOD international conference on Management of data · doi:10.1145/1376616.1376746 · Cited by 4,852 · cited 2×
“For example, knowledge bases (KB), such as Freebase (Bollacker et al., 2008), YAGO (Suchanek et al.”
BackgroundReading Wikipedia to answer open-domain questions
Chen, D., Fisch, A., Weston, J., & Bordes, A. (2017) · Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/p17-1171 · Cited by 1,546 · cited 4×
“Open-domain question answering (QA) against a text corpus (Chen et al., 2017; Wang et al., 2018) can also be treated as claim entailment problem, if we treat (question, correct answer) as a claim.”
BackgroundMethodInfluentialFEVER: a Large-scale Dataset for Fact Extraction and VERification
Thorne, J., Vlachos, A., Christodoulopoulos, C., & Mittal, A. (2018) · Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers) · doi:10.18653/v1/n18-1074 · Cited by 1,343 · cited 26×
“In contrast, the pipeline system by Thorne et al. (2018) has much higher recall than precision (45.89 vs. 10.79).”
BackgroundMethodInfluentialFact Checking: Task definition and dataset construction
Vlachos, A., & Riedel, S. (2014) · Proceedings of the ACL 2014 Workshop on Language Technologies and Computational Social Science · doi:10.3115/v1/w14-2508 · Cited by 402
Emergent: a novel data-set for stance classification
Ferreira, W., & Vlachos, A. (2016) · Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies · doi:10.18653/v1/n16-1138 · Cited by 360
R3: Reinforced Ranker-Reader for Open-Domain Question Answering
Wang, S., Yu, M., Guo, X., Wang, Z., Klinger, T., Zhang, W., Chang, S., Tesauro, G., Zhou, B., & Jiang, J. (2018) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v32i1.12053 · Cited by 351 · cited 1×
“Open-domain question answering (QA) against a text corpus (Yin et al., 2016; Chen et al., 2017; Wang et al., 2018) can also be treated as claim verification problem, if we treat (question, correct answer) as a claim.”
Background
Cited by
A Survey on Automated Fact-Checking
Guo, Z., Schlichtkrull, M., & Vlachos, A. (2022) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00454 · Cited by 500
A Survey on Natural Language Processing for Fake News Detection
Oshikawa, R., Qian, J., & Wang, W. Y. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1811.00770 · Cited by 270
Fine-grained Fact Verification with Kernel Graph Attention Network
Liu, Z., Xiong, C., Sun, M., & Liu, Z. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.655 · Cited by 183
“TwoWingOS (Yin and Roth, 2018) further incorporates evidence identification to improve claim verification.”
BackgroundReasoning Over Semantic-Level Graph for Fact Checking
Zhong, W., Xu, J., Tang, D., Xu, Z., Duan, N., Zhou, M., Wang, J., & Yin, J. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.549 · Cited by 151
Seeing Things from a Different Angle:Discovering Diverse Perspectives about Claims
Chen, S., Khashabi, D., Yin, W., Callison-Burch, C., & Roth, D. (2019) · Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) · doi:10.18653/v1/n19-1053 · Cited by 104
“Some recent work study jointly the problem of identifying evidence and verifying that it supports the claim (Yin and Roth, 2018).”
BackgroundSelf-citation
Metadata
- Authors
- Yin, W., & Roth, D.
- Venue
- Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
- Published
- 2018
- Pages
- 105-114
- OpenAlex
- W2886390638
- Cited by
- 75
- References
- 7
- FWCI
- 5.62
- Type
- conference paper
- Language
- en
- Open access
- hybrid
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.