R2F: A General Retrieval, Reading and Fusion Framework for Document-level Natural Language Inference

Hao Wang, Yixin Cao, Yangguang Li, Zhen Huang, Kun Wang, Jing Shao


Abstract
Document-level natural language inference (DOCNLI) is a new challenging task in natural language processing, aiming at judging the entailment relationship between a pair of hypothesis and premise documents. Current datasets and baselines largely follow sentence-level settings, but fail to address the issues raised by longer documents. In this paper, we establish a general solution, named Retrieval, Reading and Fusion (R2F) framework, and a new setting, by analyzing the main challenges of DOCNLI: interpretability, long-range dependency, and cross-sentence inference. The basic idea of the framework is to simplify document-level task into a set of sentence-level tasks, and improve both performance and interpretability with the power of evidence. For each hypothesis sentence, the framework retrieves evidence sentences from the premise, and reads to estimate its credibility. Then the sentence-level results are fused to judge the relationship between the documents. For the setting, we contribute complementary evidence and entailment label annotation on hypothesis sentences, for interpretability study. Our experimental results show that R2F framework can obtain state-of-the-art performance and is robust for diverse evidence retrieval methods. Moreover, it can give more interpretable prediction results. Our model and code are released at https://github.com/phoenixsecularbird/R2F.
Anthology ID:
2022.emnlp-main.204
Volume:
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates
Editors:
Yoav Goldberg, Zornitsa Kozareva, Yue Zhang
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3122–3134
Language:
URL:
https://aclanthology.org/2022.emnlp-main.204
DOI:
10.18653/v1/2022.emnlp-main.204
Bibkey:
Cite (ACL):
Hao Wang, Yixin Cao, Yangguang Li, Zhen Huang, Kun Wang, and Jing Shao. 2022. R2F: A General Retrieval, Reading and Fusion Framework for Document-level Natural Language Inference. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 3122–3134, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
Cite (Informal):
R2F: A General Retrieval, Reading and Fusion Framework for Document-level Natural Language Inference (Wang et al., EMNLP 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.emnlp-main.204.pdf