Publication Details

Claim-Dissector: An Interpretable Fact-Checking System with Joint Re-ranking and Veracity Prediction

FAJČÍK, M.; MOTLÍČEK, P.; SMRŽ, P. Claim-Dissector: An Interpretable Fact-Checking System with Joint Re-ranking and Veracity Prediction. In Findings of the Association for Computational Linguistics: ACL 2023. ACL. Toronto: Association for Computational Linguistics, 2023. p. 10184-10205. ISBN: 978-1-959429-62-3.
Czech title
Claim-Dissector: Interpretabilní systém pro ověřování faktů se současným řazením relevance a predikcí pravdivosti
Type
conference paper
Language
English
Authors
URL
Keywords

fact-checking, open-domain fact-checking, claim, claim-dissector, dissector,
fine-grained retrieval, coarse-grained supervision, interpretability,
interpretable retrieval, evidence-grounded prediction, verification, fact
verification, veracity assessement

Abstract

We present Claim-Dissector: a novel latent variable model for fact-checking and
analysis, which given a claim and a set of retrieved evidence jointly learns to
identify: (i) the relevant evidences to the given claim (ii) the veracity of the
claim. We propose to disentangle the per-evidence relevance probability and its
contribution to the final veracity probability in an interpretable way - the
final veracity probability is proportional to a linear ensemble of per-evidence
relevance probabilities. In this way, the individual contributions of evidences
towards the final predicted probability can be identified. In per-evidence
relevance probability, our model can further distinguish whether each relevant
evidence is supporting (S) or refuting (R) the claim. This allows to quantify how
much the S/R probability contributes to final verdict or to detect disagreeing
evidence. Despite its interpretable nature, our system achieves results
competetive with state-of-the-art on the FEVER dataset, as compared to typical
two-stage system pipelines, while using significantly fewer parameters.
Furthermore, our analysis shows that our model can learn fine-grained relevance
cues while using coarse-grained supervision and we demonstrate it in 2 ways. (i)
We show that our model can achieve competitive sentence recall while using only
paragraph-level relevance supervision. (ii) Traversing towards the finest
granularity of relevance, we show that our model is capable of identifying
relevance at the token level. To do this, we present a new benchmark TLR-FEVER
focusing on token-level interpretability - humans annotate tokens in relevant
evidences they considered essential when making their judgment. Then we measure
how similar are these annotations to the tokens our model is focusing on.

Published
2023
Pages
10184–10205
Proceedings
Findings of the Association for Computational Linguistics: ACL 2023
Series
ACL
Volume
2023
Conference
The 61st Annual Meeting of the Association for Computational Linguistics, Toronto, CA
ISBN
978-1-959429-62-3
Publisher
Association for Computational Linguistics
Place
Toronto
DOI
EID Scopus
BibTeX
@inproceedings{BUT185594,
  author="Martin {Fajčík} and Petr {Motlíček} and Pavel {Smrž}",
  title="Claim-Dissector: An Interpretable Fact-Checking System with Joint Re-ranking and Veracity Prediction",
  booktitle="Findings of the Association for Computational Linguistics: ACL 2023",
  year="2023",
  series="ACL",
  volume="2023",
  pages="10184--10205",
  publisher="Association for Computational Linguistics",
  address="Toronto",
  doi="10.18653/v1/2023.findings-acl.647",
  isbn="978-1-959429-62-3",
  url="https://aclanthology.org/2023.findings-acl.647/"
}
Files
Back to top