Faithfulness in natural language generation: A systematic survey of analysis, evaluation and optimization methods
Natural Language Generation (NLG) has made great progress in recent years due to the
development of deep learning techniques such as pre-trained language models. This …
development of deep learning techniques such as pre-trained language models. This …
A benchmark dataset of check-worthy factual claims
In this paper we present the ClaimBuster dataset of 23,533 statements extracted from all US
general election presidential debates and annotated by human coders. The ClaimBuster …
general election presidential debates and annotated by human coders. The ClaimBuster …
Lambretta: learning to rank for Twitter soft moderation
To curb the problem of false information, social media platforms like Twitter started adding
warning labels to content discussing debunked narratives, with the goal of providing more …
warning labels to content discussing debunked narratives, with the goal of providing more …
[PDF][PDF] bigIR at CheckThat! 2020: Multilingual BERT for Ranking Arabic Tweets by Check-worthiness.
M Hasanain, T Elsayed - CLEF (working notes), 2020 - ceur-ws.org
This paper describes the third-year participation of our bigIR group at Qatar University in
CheckThat! lab at CLEF. This year we participated only in Arabic Task 1 that focuses on …
CheckThat! lab at CLEF. This year we participated only in Arabic Task 1 that focuses on …
Cross-lingual transfer learning for check-worthy claim identification over Twitter
M Hasanain, T Elsayed - arXiv preprint arXiv:2211.05087, 2022 - arxiv.org
Misinformation spread over social media has become an undeniable infodemic. However,
not all spreading claims are made equal. If propagated, some claims can be destructive, not …
not all spreading claims are made equal. If propagated, some claims can be destructive, not …
What to fact-check: Guiding check-worthy information detection in news articles through argumentative discourse structure
T Alhindi, B McManus, S Muresan - … of the 22nd Annual Meeting of …, 2021 - aclanthology.org
Most existing methods for automatic fact-checking start with a precompiled list of claims to
verify. We investigate the understudied problem of determining what statements in news …
verify. We investigate the understudied problem of determining what statements in news …
Gradient-based adversarial factual consistency evaluation for abstractive summarization
Neural abstractive summarization systems have gained significant progress in recent years.
However, abstractive summarization often produce inconsisitent statements or false facts …
However, abstractive summarization often produce inconsisitent statements or false facts …
Is checkworthiness generalizable? Evaluating task and domain generalization of datasets for claim detection
S Nenno - Neural Computing and Applications, 2024 - Springer
The spread of misinformation has reached a level at which neither research nor fact-
checkers can monitor it only manually anymore. Accordingly, there has been much research …
checkers can monitor it only manually anymore. Accordingly, there has been much research …
Propositional claim detection: a task and dataset for the classification of claims to truth
S Nenno - Journal of Computational Social Science, 2024 - Springer
Abstract This paper introduces Propositional Claim Detection (PCD), an NLP task for
classifying claims to truth, and presents a publicly available dataset for it. PCD is applicable …
classifying claims to truth, and presents a publicly available dataset for it. PCD is applicable …
Ontology Enhanced Claim Detection
ZM Hüsünbeyi, T Scheffler - arXiv preprint arXiv:2402.12282, 2024 - arxiv.org
We propose an ontology enhanced model for sentence based claim detection. We fused
ontology embeddings from a knowledge base with BERT sentence embeddings to perform …
ontology embeddings from a knowledge base with BERT sentence embeddings to perform …