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

• URL: http://arxiv.org/abs/2210.12328v1
• Date: Sat, 22 Oct 2022 02:02:35 GMT
• Title: R$^2$F: A General Retrieval, Reading and Fusion Framework for Document-level Natural Language Inference
• Authors: Hao Wang, Yixin Cao, Yangguang Li, Zhen Huang, Kun Wang, Jing Shao
• Abstract summary: Document-level natural language inference (DOCNLI) is a new challenging task in natural language processing. We establish a general solution, named Retrieval, Reading and Fusion (R2F) framework, and a new setting. Our experimental results show that R2F framework can obtain state-of-the-art performance and is robust for diverse evidence retrieval methods.
• Score: 29.520857954199904
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• Fine-Grained Natural Language Inference Based Faithfulness Evaluation for Diverse Summarisation Tasks [14.319567507959759]
  We study existing approaches to leverage off-the-shelf Natural Language Inference (NLI) models for the evaluation of summary faithfulness. We propose a novel approach, namely InFusE, that uses a variable premise size and simplifies summary sentences into shorter hypotheses.
  arXiv  Detail & Related papers  (2024-02-27T15:57:11Z)
• PropSegmEnt: A Large-Scale Corpus for Proposition-Level Segmentation and Entailment Recognition [63.51569687229681]
  We argue for the need to recognize the textual entailment relation of each proposition in a sentence individually. We propose PropSegmEnt, a corpus of over 45K propositions annotated by expert human raters. Our dataset structure resembles the tasks of (1) segmenting sentences within a document to the set of propositions, and (2) classifying the entailment relation of each proposition with respect to a different yet topically-aligned document.
  arXiv  Detail & Related papers  (2022-12-21T04:03:33Z)
• Document-Level Relation Extraction with Sentences Importance Estimation and Focusing [52.069206266557266]
  Document-level relation extraction (DocRE) aims to determine the relation between two entities from a document of multiple sentences. We propose a Sentence Estimation and Focusing (SIEF) framework for DocRE, where we design a sentence importance score and a sentence focusing loss. Experimental results on two domains show that our SIEF not only improves overall performance, but also makes DocRE models more robust.
  arXiv  Detail & Related papers  (2022-04-27T03:20:07Z)
• GERE: Generative Evidence Retrieval for Fact Verification [57.78768817972026]
  We propose GERE, the first system that retrieves evidences in a generative fashion. The experimental results on the FEVER dataset show that GERE achieves significant improvements over the state-of-the-art baselines.
  arXiv  Detail & Related papers  (2022-04-12T03:49:35Z)
• Long Document Summarization with Top-down and Bottom-up Inference [113.29319668246407]
  We propose a principled inference framework to improve summarization models on two aspects. Our framework assumes a hierarchical latent structure of a document where the top-level captures the long range dependency. We demonstrate the effectiveness of the proposed framework on a diverse set of summarization datasets.
  arXiv  Detail & Related papers  (2022-03-15T01:24:51Z)
• Eider: Evidence-enhanced Document-level Relation Extraction [56.71004595444816]
  Document-level relation extraction (DocRE) aims at extracting semantic relations among entity pairs in a document. We propose a three-stage evidence-enhanced DocRE framework consisting of joint relation and evidence extraction, evidence-centered relation extraction (RE), and fusion of extraction results.
  arXiv  Detail & Related papers  (2021-06-16T09:43:16Z)
• LESA: Linguistic Encapsulation and Semantic Amalgamation Based Generalised Claim Detection from Online Content [15.814664354258184]
  LESA aims at advancing headfirst into expunging the former issue by assembling a source-independent generalized model. We resolve the latter issue by annotating a Twitter dataset which aims at providing a testing ground on a large unstructured dataset. Experimental results show that LESA improves upon the state-of-the-art performance across six benchmark claim datasets.
  arXiv  Detail & Related papers  (2021-01-28T09:51:30Z)
• L2R2: Leveraging Ranking for Abductive Reasoning [65.40375542988416]
  The abductive natural language inference task ($alpha$NLI) is proposed to evaluate the abductive reasoning ability of a learning system. A novel $L2R2$ approach is proposed under the learning-to-rank framework. Experiments on the ART dataset reach the state-of-the-art in the public leaderboard.
  arXiv  Detail & Related papers  (2020-05-22T15:01:23Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.