{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,16]],"date-time":"2025-04-16T06:00:22Z","timestamp":1744783222435,"version":"3.37.3"},"reference-count":53,"publisher":"MDPI AG","issue":"10","license":[{"start":{"date-parts":[[2021,5,16]],"date-time":"2021-05-16T00:00:00Z","timestamp":1621123200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"Fact verification aims to verify the authenticity of a given claim based on the retrieved evidence from Wikipedia articles. Existing works mainly focus on enhancing the semantic representation of evidence, e.g., introducing the graph structure to model the evidence relation. However, previous methods can\u2019t well distinguish semantic-similar claims and evidences with distinct authenticity labels. In addition, the performances of graph-based models are limited by the over-smoothing problem of graph neural networks. To this end, we propose a graph-based contrastive learning method for fact verification abbreviated as CosG, which introduces a contrastive label-supervised task to help the encoder learn the discriminative representations for different-label claim-evidence pairs, as well as an unsupervised graph-contrast task, to alleviate the unique node features loss in the graph propagation. We conduct experiments on FEVER, a large benchmark dataset for fact verification. Experimental results show the superiority of our proposal against comparable baselines, especially for the claims that need multiple-evidences to verify. In addition, CosG presents better model robustness on the low-resource scenario.<\/jats:p>","DOI":"10.3390\/s21103471","type":"journal-article","created":{"date-parts":[[2021,5,17]],"date-time":"2021-05-17T06:31:34Z","timestamp":1621233094000},"page":"3471","source":"Crossref","is-referenced-by-count":4,"title":["CosG: A Graph-Based Contrastive Learning Method for Fact Verification"],"prefix":"10.3390","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3919-8598","authenticated-orcid":false,"given":"Chonghao","family":"Chen","sequence":"first","affiliation":[{"name":"Science and Technology on Information Systems Engineering Laboratory, National University of Defense Technology, Changsha 410073, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8486-5631","authenticated-orcid":false,"given":"Jianming","family":"Zheng","sequence":"additional","affiliation":[{"name":"Science and Technology on Information Systems Engineering Laboratory, National University of Defense Technology, Changsha 410073, China"}]},{"given":"Honghui","family":"Chen","sequence":"additional","affiliation":[{"name":"Science and Technology on Information Systems Engineering Laboratory, National University of Defense Technology, Changsha 410073, China"}]}],"member":"1968","published-online":{"date-parts":[[2021,5,16]]},"reference":[{"key":"ref_1","unstructured":"Cohen, S., Li, C., Yang, J., and Yu, C. (2011, January 9\u201312). Computational Journalism: A Call to Arms to Database Researchers. Proceedings of the Fifth Biennial Conference on Innovative Data Systems Research, Asilomar, CA, USA."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Thorne, J., Vlachos, A., Christodoulopoulos, C., and Mittal, A. (2018). FEVER: A Large-scale Dataset for Fact Extraction and VERification. arXiv.","DOI":"10.18653\/v1\/N18-1074"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Thorne, J., Vlachos, A., and Cocarascu, O. (2018). The Fact Extraction and VERification (FEVER) Shared Task. arXiv.","DOI":"10.18653\/v1\/W18-5501"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Bowman, S.R., Angeli, G., Potts, C., and Manning, C.D. (2015). A large annotated corpus for learning natural language inference. arXiv.","DOI":"10.18653\/v1\/D15-1075"},{"key":"ref_5","unstructured":"Nie, Y., Chen, H., and Bansal, M. (February, January 27). Combining Fact Extraction and Verification with Neural Semantic Matching Networks. Proceedings of the AAAI Conference on Artificial Intelligence, Honolulu, HI, USA."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Nie, Y., Wang, S., and Bansal, M. (2019). Revealing the Importance of Semantic Retrieval for Machine Reading at Scale. arXiv.","DOI":"10.18653\/v1\/D19-1258"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Soleimani, A., Monz, C., and Worring, M. (2020, January 14\u201317). BERT for Evidence Retrieval and Claim Verification. Proceedings of the European Conference on Information Retrieval, Lisbon, Portugal.","DOI":"10.1007\/978-3-030-45442-5_45"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Hanselowski, A., Zhang, H., Li, Z., Sorokin, D., Schiller, B., Schulz, C., and Gurevych, I. (2018). UKP-Athene: Multi-Sentence Textual Entailment for Claim Verification. arXiv.","DOI":"10.18653\/v1\/W18-5516"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Zhou, J., Han, X., Yang, C., Liu, Z., Wang, L., Li, C., and Sun, M. (2019). GEAR: Graph-based Evidence Aggregating and Reasoning for Fact Verification. arXiv.","DOI":"10.18653\/v1\/P19-1085"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Liu, Z., Xiong, C., Sun, M., and Liu, Z. (2019). Fine-grained Fact Verification with Kernel Graph Attention Network. arXiv.","DOI":"10.18653\/v1\/2020.acl-main.655"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"102472","DOI":"10.1016\/j.ipm.2020.102472","article-title":"An entity-graph based reasoning method for fact verification","volume":"58","author":"Chen","year":"2021","journal-title":"Inf. Process. Manag."},{"key":"ref_12","unstructured":"Xiao, Y., Qu, Y., Qiu, L., Zhou, H., Li, L., Zhang, W., and Yu, Y. (2019). Dynamically Fused Graph Network for Multi-hop Reasoning. arXiv."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Li, Q., Han, Z., and Wu, X. (2018, January 2\u20137). Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learning. Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence, New Orleans, LA, USA.","DOI":"10.1609\/aaai.v32i1.11604"},{"key":"ref_14","unstructured":"Devlin, J., Chang, M., Lee, K., and Toutanova, K. (2019). BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. arXiv."},{"key":"ref_15","unstructured":"Veli\u010dkovi\u0107, P., Fedus, W., Hamilton, W.L., Li\u00f2, P., Bengio, Y., and Hjelm, R.D. (2019). Deep Graph Infomax. arXiv."},{"key":"ref_16","unstructured":"Khosla, P., Teterwak, P., Wang, C., Sarna, A., Tian, Y., Isola, P., Maschinot, A., Liu, C., and Krishnan, D. (2020). Supervised Contrastive Learning. arXiv."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Ciampaglia, G.L., Shiralkar, P., Rocha, L.M., Bollen, J., Menczer, F., and Flammini, A. (2015). Computational fact checking from knowledge networks. PLoS ONE, 10.","DOI":"10.1371\/journal.pone.0141938"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Ferreira, W., and Vlachos, A. (2016, January 12\u201317). Emergent: A novel data-set for stance classification. Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, San Diego, CA, USA.","DOI":"10.18653\/v1\/N16-1138"},{"key":"ref_19","unstructured":"Ma, J., Gao, W., Joty, S.R., and Wong, K. (August, January 28). Sentence-Level Evidence Embedding for Claim Verification with Hierarchical Attention Networks. Proceedings of the 57th Conference of the Association for Computational Linguistics, Florence, Italy."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Chen, Q., Zhu, X., Ling, Z., Wei, S., Jiang, H., and Inkpen, D. (2017). Enhanced LSTM for Natural Language Inference. arXiv.","DOI":"10.18653\/v1\/P17-1152"},{"key":"ref_21","unstructured":"Yang, Z., Dai, Z., Yang, Y., Carbonell, J., Salakhutdinov, R., and Le, Q.V. (2019). XLNet: Generalized Autoregressive Pretraining for Language Understanding. arXiv."},{"key":"ref_22","unstructured":"Kipf, T.N., and Welling, M. (2017). Semi-Supervised Classification with Graph Convolutional Networks. arXiv."},{"key":"ref_23","unstructured":"Veli\u010dkovi\u0107, P., Cucurull, G., Casanova, A., Romero, A., Lio, P., and Bengio, Y. (2018). Graph Attention Networks. arXiv."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Zhong, W., Xu, J., Tang, D., Xu, Z., Duan, N., Zhou, M., Wang, J., and Yin, J. (2019). Reasoning over Semantic-Level Graph for Fact Checking. arXiv.","DOI":"10.18653\/v1\/2020.acl-main.549"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"157140","DOI":"10.1109\/ACCESS.2020.3019586","article-title":"Robust Reasoning Over Heterogeneous Textual Information for Fact Verification","volume":"8","author":"Wang","year":"2020","journal-title":"IEEE Access"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Yin, W., and Roth, D. (2018). TwoWingOS: A Two-Wing Optimization Strategy for Evidential Claim Verification. arXiv.","DOI":"10.18653\/v1\/D18-1010"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Hidey, C., and Diab, M. (2018, January 1). Team SWEEPer: Joint Sentence Extraction and Fact Checking with Pointer Networks. Proceedings of the First Workshop on Fact Extraction and VERification (FEVER), Brussels, Belgium.","DOI":"10.18653\/v1\/W18-5525"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Nie, Y., Bauer, L., and Bansal, M. (2020, January 9). Simple Compounded-Label Training for Fact Extraction and Verification. Proceedings of the Third Workshop on Fact Extraction and VERification (FEVER), Online.","DOI":"10.18653\/v1\/2020.fever-1.1"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., Wu, Y., Xie, S., and Girshick, R. (2020, January 13\u201319). Momentum Contrast for Unsupervised Visual Representation Learning. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref_30","unstructured":"Chen, T., Kornblith, S., Norouzi, M., and Hinton, G. (2020, January 12\u201318). A Simple Framework for Contrastive Learning of Visual Representations. Proceedings of the International Conference on Machine Learning, Online."},{"key":"ref_31","unstructured":"Mikolov, T., Sutskever, I., Chen, K., Corrado, G., and Dean, J. (2013). Distributed Representations of Words and Phrases and their Compositionality. arXiv."},{"key":"ref_32","unstructured":"Gutmann, M., and Hyv\u00e4rinen, A. (2010, January 13\u201315). Noise-contrastive estimation: A new estimation principle for unnormalized statistical models. Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, Sardinia, Italy."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Wu, Z., Xiong, Y., Yu, S.X., and Lin, D. (2018). Unsupervised Feature Learning via Non-Parametric Instance Discrimination. arXiv.","DOI":"10.1109\/CVPR.2018.00393"},{"key":"ref_34","unstructured":"Hjelm, R.D., Fedorov, A., Lavoie-Marchildon, S., Grewal, K., Bachman, P., Trischler, A., and Bengio, Y. (2019). Learning deep representations by mutual information estimation and maximization. arXiv."},{"key":"ref_35","unstructured":"Bachman, P., Hjelm, R.D., and Buchwalter, W. (2019). Learning Representations by Maximizing Mutual Information Across Views. arXiv."},{"key":"ref_36","unstructured":"Hassani, K., and Ahmadi, A.H.K. (2020, January 13\u201318). Contrastive Multi-View Representation Learning on Graphs. Proceedings of the International Conference on Machine Learning, Vienna, Austria."},{"key":"ref_37","unstructured":"Tschannen, M., Djolonga, J., Rubenstein, P.K., Gelly, S., and Lucic, M. (2019). On Mutual Information Maximization for Representation Learning. arXiv."},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Noroozi, M., Vinjimoor, A., Favaro, P., and Pirsiavash, H. (2018, January 18\u201322). Boosting Self-Supervised Learning via Knowledge Transfer. Proceedings of the 2018 IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00975"},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Caron, M., Bojanowski, P., Joulin, A., and Douze, M. (2018, January 8\u201314). Deep Clustering for Unsupervised Learning of Visual Features. Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany.","DOI":"10.1007\/978-3-030-01264-9_9"},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Tian, Y., Krishnan, D., and Isola, P. (2019). Contrastive Multiview Coding. arXiv.","DOI":"10.1007\/978-3-030-58621-8_45"},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Gardner, M., Grus, J., Neumann, M., Tafjord, O., Dasigi, P., Liu, N., Peters, M., Schmitz, M., and Zettlemoyer, L. (2018). AllenNLP: A Deep Semantic Natural Language Processing Platform. arXiv.","DOI":"10.18653\/v1\/W18-2501"},{"key":"ref_42","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, L., and Polosukhin, I. (2017). Attention is All you Need. arXiv."},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Liu, Q., and Song, L. (2018). Sentence-State LSTM for Text Representation. arXiv.","DOI":"10.18653\/v1\/P18-1030"},{"key":"ref_44","doi-asserted-by":"crossref","unstructured":"Marcheggiani, D., and Titov, I. (2017). Encoding Sentences with Graph Convolutional Networks for Semantic Role Labeling. arXiv.","DOI":"10.18653\/v1\/D17-1159"},{"key":"ref_45","doi-asserted-by":"crossref","unstructured":"Bastings, J., Titov, I., Aziz, W., Marcheggiani, D., and Sima\u2019an, K. (2017). Graph Convolutional Encoders for Syntax-aware Neural Machine Translation. arXiv.","DOI":"10.18653\/v1\/D17-1209"},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Qi, P., and Manning, C.D. (2018). Graph Convolution over Pruned Dependency Trees Improves Relation Extraction. arXiv.","DOI":"10.18653\/v1\/D18-1244"},{"key":"ref_47","doi-asserted-by":"crossref","unstructured":"Marcheggiani, D., Bastings, J., and Titov, I. (2018). Exploiting Semantics in Neural Machine Translation with Graph Convolutional Networks. arXiv.","DOI":"10.18653\/v1\/N18-2078"},{"key":"ref_48","doi-asserted-by":"crossref","unstructured":"Peng, H., Li, J., He, Y., Liu, Y., Bao, M., Wang, L., Song, Y., and Yang, Q. (2018, January 23\u201327). Large-Scale Hierarchical Text Classification with Recursively Regularized Deep Graph-CNN. Proceedings of the 2018 World Wide Web Conference, Lyon, France.","DOI":"10.1145\/3178876.3186005"},{"key":"ref_49","doi-asserted-by":"crossref","unstructured":"Nguyen, T.H., and Grishman, R. (2018, January 2\u20137). Graph Convolutional Networks with Argument-Aware Pooling for Event Detection. Proceedings of the AAAI Conference on Artificial Intelligence, New Orleans, LA, USA.","DOI":"10.1609\/aaai.v32i1.12039"},{"key":"ref_50","unstructured":"Cao, N.D., Aziz, W., and Titov, I. (2018). Question Answering by Reasoning Across Documents with Graph Convolutional Networks. arXiv."},{"key":"ref_51","doi-asserted-by":"crossref","unstructured":"Chakrabarty, T., Alhindi, T., and Muresan, S. (2018, January 1). Robust Document Retrieval and Individual Evidence Modeling for Fact Extraction and Verification. Proceedings of the First Workshop on Fact Extraction and VERification (FEVER), Brussels, Belgium.","DOI":"10.18653\/v1\/W18-5521"},{"key":"ref_52","doi-asserted-by":"crossref","unstructured":"Luken, J., Jiang, N., and de Marneffe, M.C. (2018, January 1). QED: A fact verification system for the FEVER shared task. Proceedings of the First Workshop on Fact Extraction and VERification (FEVER), Brussels, Belgium.","DOI":"10.18653\/v1\/W18-5526"},{"key":"ref_53","doi-asserted-by":"crossref","unstructured":"Yoneda, T., Mitchell, J., Welbl, J., Stenetorp, P., and Riedel, S. (2018, January 1). UCL Machine Reading Group: Four Factor Framework For Fact Finding (HexaF). Proceedings of the First Workshop on Fact Extraction and VERification (FEVER), Brussels, Belgium.","DOI":"10.18653\/v1\/W18-5515"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/21\/10\/3471\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,12]],"date-time":"2024-07-12T21:42:44Z","timestamp":1720820564000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/21\/10\/3471"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5,16]]},"references-count":53,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2021,5]]}},"alternative-id":["s21103471"],"URL":"https:\/\/doi.org\/10.3390\/s21103471","relation":{},"ISSN":["1424-8220"],"issn-type":[{"type":"electronic","value":"1424-8220"}],"subject":[],"published":{"date-parts":[[2021,5,16]]}}}