PropSegmEnt: A Large-Scale Corpus for Proposition-Level Segmentation and Entailment Recognition
원문 초록
The widely studied task of Natural Language Inference (NLI) requires a system to recognize whether one piece of text is textually entailed by another, i.e. whether the entirety of its meaning can be inferred from the other. In current NLI datasets and models, textual entailment relations are typically defined on the sentence- or paragraph-level. However, even a simple sentence often contains multiple propositions, i.e. distinct units of meaning conveyed by the sentence. As these propositions can carry different truth values in the context of a given premise, 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, i.e. documents describing the same event or entity. We establish strong baselines for the segmentation and entailment tasks. Through case studies on summary hallucination detection and document-level NLI, we demonstrate that our conceptual framework is potentially useful for understanding and explaining the compositionality of NLI labels.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
A MISMATCHED Benchmark for Scientific Natural Language Inference
Mitigating Object Hallucinations via Sentence-Level Early Intervention
DiscoSG: Towards Discourse-Level Text Scene Graph Parsing through Iterative Graph Refinement
MedScore: Factuality Evaluation of Free-Form Medical Answers
Thunder-NUBench: A Benchmark for LLMs' Sentence-Level Negation Understanding
Conservative Bias in Large Language Models: Measuring Relation Predictions
토론
이 논문과 연결된 포럼 글이 아직 없습니다.