Detail publikace

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

FAJČÍK, M. MOTLÍČEK, P. SMRŽ, P.

Originální název

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

Typ

článek ve sborníku ve WoS nebo Scopus

Jazyk

angličtina

Originální abstrakt

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.

Klíčová slova

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

Autoři

FAJČÍK, M.; MOTLÍČEK, P.; SMRŽ, P.

Vydáno

6. 7. 2023

Nakladatel

Association for Computational Linguistics

Místo

Toronto

ISBN

978-1-959429-62-3

Kniha

Findings of the Association for Computational Linguistics: ACL 2023

Edice

ACL

Strany od

10184

Strany do

10205

Strany počet

22

URL

https://aclanthology.org/2023.findings-acl.647/

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/"
}