Sentence-Level Evidence Embedding for Claim Verification with Hierarchical Attention Networks

Jing Ma; Wei Gao; Shafiq Joty; Kam Fai Wong

doi:10.18653/v1/P19-1244

Sentence-Level Evidence Embedding for Claim Verification with Hierarchical Attention Networks

Jing Ma
, Wei Gao
, Shafiq Joty
, Kam Fai Wong

Department of Computer Science

Research output: Chapter in book/report/conference proceeding › Conference proceeding › peer-review

92 Citations (Scopus)

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 pieces of evidence, 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 evidence as well as their semantic relatedness with the claim. Our model consists of three main components: 1) A coherence-based attention layer embeds coherent evidence 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 embedded evidence. Experimental results on three public benchmark datasets show that our proposed model outperforms a set of state-of-the-art baselines.

Original language	English
Title of host publication	Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
Editors	Anna Korhonen, David Traum, Lluís Màrquez
Place of Publication	Florence
Publisher	Association for Computational Linguistics (ACL)
Pages	2561-2571
Number of pages	11
ISBN (Electronic)	9781950737482
DOIs	https://doi.org/10.18653/v1/P19-1244
Publication status	Published - Jul 2019
Event	57th Annual Meeting of the Association for Computational Linguistic - Fortezza da Basso, Florence, Italy Duration: 28 Jul 2019 → 2 Aug 2019 https://acl2019.org/EN/index.xhtml.html (Conference website) https://acl2019.org/schedule.acl2019.org/index.html (Conference schedule) https://aclanthology.org/volumes/P19-1/ (Conference proceeding)

Publication series

Name	Proceedings of Annual Meeting of the Association for Computational Linguistics
Publisher	Association for Computational Linguistics

Conference

Conference	57th Annual Meeting of the Association for Computational Linguistic
Abbreviated title	ACL 2019
Country/Territory	Italy
City	Florence
Period	28/07/19 → 2/08/19
Internet address	https://acl2019.org/EN/index.xhtml.html (Conference website) https://acl2019.org/schedule.acl2019.org/index.html (Conference schedule) https://aclanthology.org/volumes/P19-1/ (Conference proceeding)

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.18653/v1/P19-1244Licence: CC BY

Cite this

Ma, J., Gao, W., Joty, S., & Wong, K. F. (2019). Sentence-Level Evidence Embedding for Claim Verification with Hierarchical Attention Networks. In A. Korhonen, D. Traum, & L. Màrquez (Eds.), Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics (pp. 2561-2571). (Proceedings of Annual Meeting of the Association for Computational Linguistics). Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/P19-1244

Ma, Jing ; Gao, Wei ; Joty, Shafiq et al. / Sentence-Level Evidence Embedding for Claim Verification with Hierarchical Attention Networks. Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. editor / Anna Korhonen ; David Traum ; Lluís Màrquez. Florence : Association for Computational Linguistics (ACL), 2019. pp. 2561-2571 (Proceedings of Annual Meeting of the Association for Computational Linguistics).

@inproceedings{ba8f0c051c974ab4b479db6fae4f2618,

title = "Sentence-Level Evidence Embedding for Claim Verification with Hierarchical Attention Networks",

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 pieces of evidence, 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 evidence as well as their semantic relatedness with the claim. Our model consists of three main components: 1) A coherence-based attention layer embeds coherent evidence 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 embedded evidence. Experimental results on three public benchmark datasets show that our proposed model outperforms a set of state-of-the-art baselines.",

author = "Jing Ma and Wei Gao and Shafiq Joty and Wong, \{Kam Fai\}",

note = "This work was partly supported by Hong Kong RGC GRF (14232816, 14209416, 14204118), NSFC (61877020) and SCSE-SUG grant M4082038 at NTU. Publisher Copyright: {\textcopyright} 2019 Association for Computational Linguistics.; 57th Annual Meeting of the Association for Computational Linguistic, ACL 2019 ; Conference date: 28-07-2019 Through 02-08-2019",

year = "2019",

month = jul,

doi = "10.18653/v1/P19-1244",

language = "English",

series = "Proceedings of Annual Meeting of the Association for Computational Linguistics",

publisher = "Association for Computational Linguistics (ACL)",

pages = "2561--2571",

editor = "Anna Korhonen and David Traum and Llu{\'i}s M{\`a}rquez",

booktitle = "Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics",

address = "United States",

url = "https://acl2019.org/EN/index.xhtml.html, https://acl2019.org/schedule.acl2019.org/index.html, https://aclanthology.org/volumes/P19-1/",

}

Ma, J, Gao, W, Joty, S & Wong, KF 2019, Sentence-Level Evidence Embedding for Claim Verification with Hierarchical Attention Networks. in A Korhonen, D Traum & L Màrquez (eds), Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. Proceedings of Annual Meeting of the Association for Computational Linguistics, Association for Computational Linguistics (ACL), Florence, pp. 2561-2571, 57th Annual Meeting of the Association for Computational Linguistic, Florence, Italy, 28/07/19. https://doi.org/10.18653/v1/P19-1244

Sentence-Level Evidence Embedding for Claim Verification with Hierarchical Attention Networks. / Ma, Jing; Gao, Wei; Joty, Shafiq et al.
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. ed. / Anna Korhonen; David Traum; Lluís Màrquez. Florence: Association for Computational Linguistics (ACL), 2019. p. 2561-2571 (Proceedings of Annual Meeting of the Association for Computational Linguistics).

Research output: Chapter in book/report/conference proceeding › Conference proceeding › peer-review

TY - GEN

T1 - Sentence-Level Evidence Embedding for Claim Verification with Hierarchical Attention Networks

AU - Ma, Jing

AU - Gao, Wei

AU - Joty, Shafiq

AU - Wong, Kam Fai

N1 - This work was partly supported by Hong Kong RGC GRF (14232816, 14209416, 14204118), NSFC (61877020) and SCSE-SUG grant M4082038 at NTU. Publisher Copyright: © 2019 Association for Computational Linguistics.

PY - 2019/7

Y1 - 2019/7

N2 - 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 pieces of evidence, 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 evidence as well as their semantic relatedness with the claim. Our model consists of three main components: 1) A coherence-based attention layer embeds coherent evidence 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 embedded evidence. Experimental results on three public benchmark datasets show that our proposed model outperforms a set of state-of-the-art baselines.

AB - 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 pieces of evidence, 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 evidence as well as their semantic relatedness with the claim. Our model consists of three main components: 1) A coherence-based attention layer embeds coherent evidence 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 embedded evidence. Experimental results on three public benchmark datasets show that our proposed model outperforms a set of state-of-the-art baselines.

UR - https://www.scopus.com/pages/publications/85084044172

UR - https://aclanthology.org/P19-1244/

U2 - 10.18653/v1/P19-1244

DO - 10.18653/v1/P19-1244

M3 - Conference proceeding

AN - SCOPUS:85084044172

T3 - Proceedings of Annual Meeting of the Association for Computational Linguistics

SP - 2561

EP - 2571

BT - Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

A2 - Korhonen, Anna

A2 - Traum, David

A2 - Màrquez, Lluís

PB - Association for Computational Linguistics (ACL)

CY - Florence

T2 - 57th Annual Meeting of the Association for Computational Linguistic

Y2 - 28 July 2019 through 2 August 2019

ER -

Ma J, Gao W, Joty S, Wong KF. Sentence-Level Evidence Embedding for Claim Verification with Hierarchical Attention Networks. In Korhonen A, Traum D, Màrquez L, editors, Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. Florence: Association for Computational Linguistics (ACL). 2019. p. 2561-2571. (Proceedings of Annual Meeting of the Association for Computational Linguistics). doi: 10.18653/v1/P19-1244

Sentence-Level Evidence Embedding for Claim Verification with Hierarchical Attention Networks

Abstract

Publication series

Conference

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this