Fact Checking with Insufficient Evidence
Research output: Contribution to journal › Journal article › Research › peer-review
Standard
Fact Checking with Insufficient Evidence. / Atanasova, Pepa; Simonsen, Jakob Grue; Lioma, Christina; Augenstein, Isabelle.
In: Transactions of the Association for Computational Linguistics, Vol. 10, 2022, p. 746-763.Research output: Contribution to journal › Journal article › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - JOUR
T1 - Fact Checking with Insufficient Evidence
AU - Atanasova, Pepa
AU - Simonsen, Jakob Grue
AU - Lioma, Christina
AU - Augenstein, Isabelle
N1 - Publisher Copyright: © MIT Press Journals. All rights reserved.
PY - 2022
Y1 - 2022
N2 - Automating the fact checking (FC) process relies on information obtained from external sources. In this work, we posit that it is crucial for FC models to make veracity predictions only when there is sufficient evidence and otherwise indicate when it is not enough. To this end, we are the first to study what information FC models consider sufficient by introducing a novel task and advancing it with three main contributions. First, we conduct an in-depth empirical analysis of the task with a new fluency-preserving method for omitting information from the evidence at the constituent and sentence level. We identify when models consider the remaining evidence (in)sufficient for FC, based on three trained models with different Transformer architectures and three FC datasets. Second, we ask annotators whether the omitted evidence was important for FC, resulting in a novel diagnostic dataset, Suffi-cientFacts1, for FC with omitted evidence. We find that models are least successful in detecting missing evidence when adverbial modifiers are omitted (21% accuracy), whereas it is easiest for omitted date modifiers (63% accuracy). Finally, we propose a novel data augmentation strategy for contrastive self-learning of missing evidence by employing the proposed omission method combined with tri-training. It improves performance for Evidence Sufficiency Prediction by up to 17.8 F1 score, which in turn improves FC performance by up to 2.6 F1 score.
AB - Automating the fact checking (FC) process relies on information obtained from external sources. In this work, we posit that it is crucial for FC models to make veracity predictions only when there is sufficient evidence and otherwise indicate when it is not enough. To this end, we are the first to study what information FC models consider sufficient by introducing a novel task and advancing it with three main contributions. First, we conduct an in-depth empirical analysis of the task with a new fluency-preserving method for omitting information from the evidence at the constituent and sentence level. We identify when models consider the remaining evidence (in)sufficient for FC, based on three trained models with different Transformer architectures and three FC datasets. Second, we ask annotators whether the omitted evidence was important for FC, resulting in a novel diagnostic dataset, Suffi-cientFacts1, for FC with omitted evidence. We find that models are least successful in detecting missing evidence when adverbial modifiers are omitted (21% accuracy), whereas it is easiest for omitted date modifiers (63% accuracy). Finally, we propose a novel data augmentation strategy for contrastive self-learning of missing evidence by employing the proposed omission method combined with tri-training. It improves performance for Evidence Sufficiency Prediction by up to 17.8 F1 score, which in turn improves FC performance by up to 2.6 F1 score.
UR - http://www.scopus.com/inward/record.url?scp=85130111577&partnerID=8YFLogxK
U2 - 10.1162/tacl_a_00486
DO - 10.1162/tacl_a_00486
M3 - Journal article
AN - SCOPUS:85130111577
VL - 10
SP - 746
EP - 763
JO - Transactions of the Association for Computational Linguistics
JF - Transactions of the Association for Computational Linguistics
SN - 2307-387X
ER -
ID: 318866287