Unsupervised Question Answering for Fact-Checking
원문 초록
Recent Deep Learning (DL) models have succeeded in achieving human-level accuracy on various natural language tasks such as question-answering, natural language inference (NLI), and textual entailment. These tasks not only require the contextual knowledge but also the reasoning abilities to be solved efficiently. In this paper, we propose an unsupervised question-answering based approach for a similar task, fact-checking. We transform the FEVER dataset into a Cloze-task by masking named entities provided in the claims. To predict the answer token, we utilize pre-trained Bidirectional Encoder Representations from Transformers (BERT). The classifier computes label based on the correctly answered questions and a threshold. Currently, the classifier is able to classify the claims as "SUPPORTS" and "MANUAL_REVIEW". This approach achieves a label accuracy of 80.2% on the development set and 80.25% on the test set of the transformed dataset.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
DS@GT at CheckThat! 2025: Evaluating Context and Tokenization Strategies for Numerical Fact Verification
Drop Dropout on Single-Epoch Language Model Pretraining
Improving Reliability and Explainability of Medical Question Answering through Atomic Fact Checking in Retrieval-Augmented LLMs
S2LPP: Small-to-Large Prompt Prediction across LLMs
LogiQA 2.0—An Improved Dataset for Logical Reasoning in Natural Language Understanding
Text-Embedded Bilinear Model for Fine-Grained Visual Recognition
토론
이 논문과 연결된 포럼 글이 아직 없습니다.