GLAF: Global-to-Local Aggregation and Fission Network for Semantic Level Fact Verification

Zhiyuan Ma, Jianjun Li, Guohui Li, Yongjing Cheng


Abstract
Accurate fact verification depends on performing fine-grained reasoning over crucial entities by capturing their latent logical relations hidden in multiple evidence clues, which is generally lacking in existing fact verification models. In this work, we propose a novel Global-to-Local Aggregation and Fission network (GLAF) to fill this gap. Instead of treating entire sentences or all semantic elements within them as nodes to construct a coarse-grained or unstructured evidence graph as in previous methods, GLAF constructs a fine-grained and structured evidence graph by parsing the rambling sentences into structural triple-level reasoning clues and regarding them as graph nodes to achieve fine-grained and interpretable evidence graph reasoning. Specifically, to capture latent logical relations between the clues, GLAF first employs a local fission reasoning layer to conduct fine-grained multi-hop reasoning, and then uses a global evidence aggregation layer to achieve information sharing and the interchange of evidence clues for final claim label prediction. Experimental results on the FEVER dataset demonstrate the effectiveness of GLAF, showing that it achieves the state-of-the-art performance by obtaining a 77.62% FEVER score.
Anthology ID:
2022.coling-1.155
Volume:
Proceedings of the 29th International Conference on Computational Linguistics
Month:
October
Year:
2022
Address:
Gyeongju, Republic of Korea
Venue:
COLING
SIG:
Publisher:
International Committee on Computational Linguistics
Note:
Pages:
1801–1812
Language:
URL:
https://aclanthology.org/2022.coling-1.155
DOI:
Bibkey:
Cite (ACL):
Zhiyuan Ma, Jianjun Li, Guohui Li, and Yongjing Cheng. 2022. GLAF: Global-to-Local Aggregation and Fission Network for Semantic Level Fact Verification. In Proceedings of the 29th International Conference on Computational Linguistics, pages 1801–1812, Gyeongju, Republic of Korea. International Committee on Computational Linguistics.
Cite (Informal):
GLAF: Global-to-Local Aggregation and Fission Network for Semantic Level Fact Verification (Ma et al., COLING 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.coling-1.155.pdf
Data
FEVER