Sentence-level evidence embedding for claim verification with hierarchical attention networks

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...

Full description

Saved in:
Bibliographic Details
Main Authors: MA, Jing, GAO, Wei, JOTY, Shafiq, WONG, Kam-Fai
Format: text
Language:English
Published: Institutional Knowledge at Singapore Management University 2019
Subjects:
Online Access:https://ink.library.smu.edu.sg/sis_research/4557
https://ink.library.smu.edu.sg/context/sis_research/article/5560/viewcontent/P19_1244.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Singapore Management University
Language: English
id sg-smu-ink.sis_research-5560
record_format dspace
spelling sg-smu-ink.sis_research-55602019-12-26T08:33:38Z Sentence-level evidence embedding for claim verification with hierarchical attention networks MA, Jing GAO, Wei JOTY, Shafiq WONG, Kam-Fai 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. 2019-08-02T07:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/4557 info:doi/10.18653/v1/P19-1244 https://ink.library.smu.edu.sg/context/sis_research/article/5560/viewcontent/P19_1244.pdf http://creativecommons.org/licenses/by-nc-nd/4.0/ Research Collection School Of Computing and Information Systems eng Institutional Knowledge at Singapore Management University Databases and Information Systems
institution Singapore Management University
building SMU Libraries
continent Asia
country Singapore
Singapore
content_provider SMU Libraries
collection InK@SMU
language English
topic Databases and Information Systems
spellingShingle Databases and Information Systems
MA, Jing
GAO, Wei
JOTY, Shafiq
WONG, Kam-Fai
Sentence-level evidence embedding for claim verification with hierarchical attention networks
description 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.
format text
author MA, Jing
GAO, Wei
JOTY, Shafiq
WONG, Kam-Fai
author_facet MA, Jing
GAO, Wei
JOTY, Shafiq
WONG, Kam-Fai
author_sort MA, Jing
title Sentence-level evidence embedding for claim verification with hierarchical attention networks
title_short Sentence-level evidence embedding for claim verification with hierarchical attention networks
title_full Sentence-level evidence embedding for claim verification with hierarchical attention networks
title_fullStr Sentence-level evidence embedding for claim verification with hierarchical attention networks
title_full_unstemmed Sentence-level evidence embedding for claim verification with hierarchical attention networks
title_sort sentence-level evidence embedding for claim verification with hierarchical attention networks
publisher Institutional Knowledge at Singapore Management University
publishDate 2019
url https://ink.library.smu.edu.sg/sis_research/4557
https://ink.library.smu.edu.sg/context/sis_research/article/5560/viewcontent/P19_1244.pdf
_version_ 1770574913630896128