Skip to content

Read-only version: For security reasons, the Research Information System (FIS) has been temporarily replaced by this read-only version. All public content and full texts remain available; login, editing, submission and statistics are not available. Questions: fis@uni-bamberg.de

Home › Publications › An Entity-based Claim Extraction Pipeline for Real-world Biomedical Fact-checking

Publication

An Entity-based Claim Extraction Pipeline for Real-world Biomedical Fact-checking

Wührl, Amelie; Grimminger, Lara; Klinger, Roman (2023): An Entity-based Claim Extraction Pipeline for Real-world Biomedical Fact-checking, in: Mubashara Akhtar, Rami Aly, Christos Christodoulopoulus, u. a. (Hrsg.), Proceedings of the Sixth Fact Extraction and VERification Workshop (FEVER), Dubrovnik: Association for Computational Linguistics, S. 29–37, doi: 10.18653/v1/2023.fever-1.3.

Details

Author
Wührl, Amelie
Grimminger, Lara
Title of the compilation
Proceedings of the Sixth Fact Extraction and VERification Workshop (FEVER)
Editors
Akhtar, Mubashara; Aly, Rami; Christodoulopoulus, Christos; Cocarascu, Oana; Guo, Zhijiang; Mittal, Arpit; Schlichtkrull, Michael; Thorne, James; Vlachos, Andreas
Conference
Sixth Fact Extraction and VERification Workshop (FEVER), Mai 2023, Dubrovnik
Publisher Information
Association for Computational Linguistics : Dubrovnik
Year of publication
2023
Language
English
DOI
URL
Abstract

Existing fact-checking models for biomedical claims are typically trained on synthetic or well-worded data and hardly transfer to social media content. This mismatch can be mitigated by adapting the social media input to mimic the focused nature of common training claims. To do so, Wührl and Klinger (2022a) propose to extract concise claims based on medical entities in the text. However, their study has two limitations: First, it relies on gold-annotated entities. Therefore, its feasibility for a real-world application cannot be assessed since this requires detecting relevant entities automatically. Second, they represent claim entities with the original tokens. This constitutes a terminology mismatch which potentially limits the fact-checking performance. To understand both challenges, we propose a claim extraction pipeline for medical tweets that incorporates named entity recognition and terminology normalization via entity linking. We show that automatic NER does lead to a performance drop in comparison to using gold annotations but the fact-checking performance still improves considerably over inputting the unchanged tweets. Normalizing entities to their canonical forms does, however, not improve the performance.

GND Keywords
Computerlinguistik
Named Entity Recognition
Keywords
entity-based Claim Extraction Pipeline
DDC Classification
004 Computer science
RVK Classification
ST 306
Peer Reviewed
yes
International Distribution
yes
Open Access Journal
yes
Type
Conferenceobject
URI
Activation date
2024-03-07
Project(s)

Permalink: https://fis.uni-bamberg.de/handle/uniba/93880 · Data as JSON · Cite: BibTeX · RIS

Data as of: 2026-11-16

Restricted read-only access: login, editing and submission are temporarily disabled.