R$^2$F: A General Retrieval, Reading and Fusion Framework for Document-level Natural Language Inference

October 22, 2022 ยท Entered Twilight ยท ๐Ÿ› Conference on Empirical Methods in Natural Language Processing

๐Ÿ’ค TWILIGHT: Eternal Rest
Repo abandoned since publication

Repo contents: README.md, bm25_retrieval, dataset, random_retrieval, rouge_retrieval, sup_simcse_retrieval, unsup_simcse_retrieval

Authors Hao Wang, Yixin Cao, Yangguang Li, Zhen Huang, Kun Wang, Jing Shao arXiv ID 2210.12328 Category cs.CL: Computation & Language Citations 0 Venue Conference on Empirical Methods in Natural Language Processing Repository https://github.com/phoenixsecularbird/R2F โญ 4 Last Checked 1 month ago
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.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

๐Ÿ“œ Similar Papers

In the same crypt โ€” Computation & Language

๐ŸŒ… ๐ŸŒ… Old Age

Attention Is All You Need

Ashish Vaswani, Noam Shazeer, ... (+6 more)

cs.CL ๐Ÿ› NeurIPS ๐Ÿ“š 166.0K cites 8 years ago