Nothing Special   »   [go: up one dir, main page]

MuGER2: Multi-Granularity Evidence Retrieval and Reasoning for Hybrid Question Answering

Yingyao Wang, Junwei Bao, Chaoqun Duan, Youzheng Wu, Xiaodong He, Tiejun Zhao


Abstract
Hybrid question answering (HQA) aims to answer questions over heterogeneous data, including tables and passages linked to table cells. The heterogeneous data can provide different granularity evidence to HQA models, e.t., column, row, cell, and link. Conventional HQA models usually retrieve coarse- or fine-grained evidence to reason the answer. Through comparison, we find that coarse-grained evidence is easier to retrieve but contributes less to the reasoner, while fine-grained evidence is the opposite. To preserve the advantage and eliminate the disadvantage of different granularity evidence, we propose MuGER2, a Multi-Granularity Evidence Retrieval and Reasoning approach. In evidence retrieval, a unified retriever is designed to learn the multi-granularity evidence from the heterogeneous data. In answer reasoning, an evidence selector is proposed to navigate the fine-grained evidence for the answer reader based on the learned multi-granularity evidence. Experiment results on the HybridQA dataset show that MuGER2 significantly boosts the HQA performance. Further ablation analysis verifies the effectiveness of both the retrieval and reasoning designs.
Anthology ID:
2022.findings-emnlp.498
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2022
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates
Editors:
Yoav Goldberg, Zornitsa Kozareva, Yue Zhang
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
6687–6697
Language:
URL:
https://aclanthology.org/2022.findings-emnlp.498
DOI:
10.18653/v1/2022.findings-emnlp.498
Bibkey:
Cite (ACL):
Yingyao Wang, Junwei Bao, Chaoqun Duan, Youzheng Wu, Xiaodong He, and Tiejun Zhao. 2022. MuGER2: Multi-Granularity Evidence Retrieval and Reasoning for Hybrid Question Answering. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 6687–6697, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
Cite (Informal):
MuGER2: Multi-Granularity Evidence Retrieval and Reasoning for Hybrid Question Answering (Wang et al., Findings 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.findings-emnlp.498.pdf