English

A Multi-Level Attention Model for Evidence-Based Fact Checking

Computation and Language 2021-06-03 v1

Abstract

Evidence-based fact checking aims to verify the truthfulness of a claim against evidence extracted from textual sources. Learning a representation that effectively captures relations between a claim and evidence can be challenging. Recent state-of-the-art approaches have developed increasingly sophisticated models based on graph structures. We present a simple model that can be trained on sequence structures. Our model enables inter-sentence attentions at different levels and can benefit from joint training. Results on a large-scale dataset for Fact Extraction and VERification (FEVER) show that our model outperforms the graph-based approaches and yields 1.09% and 1.42% improvements in label accuracy and FEVER score, respectively, over the best published model.

Keywords

Cite

@article{arxiv.2106.00950,
  title  = {A Multi-Level Attention Model for Evidence-Based Fact Checking},
  author = {Canasai Kruengkrai and Junichi Yamagishi and Xin Wang},
  journal= {arXiv preprint arXiv:2106.00950},
  year   = {2021}
}

Comments

Findings of ACL 2021

R2 v1 2026-06-24T02:44:17.704Z