Claim verification is generally a task of verifying the veracity of a given claim, which is critical to many downstream applications. It is cumbersome and inefficient for human fact-checkers to find consistent evidences, from which solid verdict could be inferred against the claim. In this paper, we propose a novel end-to-end hierarchical attention network focusing on learning to represent coherent evidences as well as their semantic relatedness with the claim. Our model consists of three main components: 1) A coherence-based attention layer embeds coherent evidences considering the claim and sentences from relevant articles; 2) An entailment-based attention layer attends on sentences that can semantically infer the claim on top of the first attention; and 3) An output layer predicts the verdict based on the the embedded evidences. Experimental results on three public benchmark datasets show that our proposed model outperforms a set of state-of-the-art baselines.

@inproceedings{jing-et-al-acl-19, abstract = {Claim verification is generally a task of verifying the veracity of a given claim, which is critical to many downstream applications. It is cumbersome and inefficient for human fact-checkers to find consistent evidences, from which solid verdict could be inferred against the claim. In this paper, we propose a novel end-to-end hierarchical attention network focusing on learning to represent coherent evidences as well as their semantic relatedness with the claim. Our model consists of three main components: 1) A coherence-based attention layer embeds coherent evidences considering the claim and sentences from relevant articles; 2) An entailment-based attention layer attends on sentences that can semantically infer the claim on top of the first attention; and 3) An output layer predicts the verdict based on the the embedded evidences. Experimental results on three public benchmark datasets show that our proposed model outperforms a set of state-of-the-art baselines.}, address = {Florence, Italy}, author = {Jing Ma and Wei Gao and Shafiq Joty and Kam-Fai Wong}, booktitle = {Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics}, numpages = {9}, pages = {2561–2571}, publisher = {ACL}, series = {ACL'19}, title = {Sentence-Level Evidence Embedding for End-to-End Claim Verification with Hierarchical Attention Networks}, url = {https://www.aclweb.org/anthology/P19-1244/}, year = {2019} }