[Invited Speaker] Automatic Fact Verification across Languages and Modality

講演者：Junichi Yamagishi
会議名：Speech processing in the large model era workshop
主催者：The School of Data Science (SDS), The Chinese University of Hong Kong, Shenzhen
開催地：深圳, 中国
開催日：2024年12月6日
URL：https://sds.cuhk.edu.cn/event/2062

Evidence-based fact-checking aims to automatically verify the veracity of input claims using evidences extracted from knowledge databases. In this talk, we present the details of our proposed automatic fact-checking model [1] and its multilingual extension to Spanish, French, Indonesian, Chinese and Japanese [2], as well as to a multimodal model that simultaneously uses structured tabular data as well as text [3]. Furthermore, a comparison between supervised trained models and LLM-based models with in-context learning is presented, and their advantages and disadvantages are discussed.

[1] Canasai Kruengkrai, Xin Wang, Junichi Yamagishi, “A Multi-Level Attention Model for Evidence-Based Fact Checking” Findings of ACL2021 Aug. 2021
[2] Yi-Chen Chang, Canasai Kruengkrai, Junichi Yamagishi, “XFEVER: Exploring Fact Verification across Languages” THE 35TH CONFERENCE ON COMPUTATIONAL LINGUISTICS AND SPEECH PROCESSING (ROCLING 2023) Oct. 2023
[3] Shirin Dabbaghi, Canasai Kruengkrai, Ramin Yahyapour, Junichi Yamagishi, “Bridging Textual and Tabular Worlds for Fact Verification: A Lightweight, Attention-Based Model” 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024) May 2024