Improving Zero-shot Sentence Decontextualisation with Content Selection and Planning

ACL ARR 2025 February Submission3360 Authors

Abstract: Extracting individual sentences from a document as evidence or reasoning steps is commonly done in many NLP tasks. However, extracted sentences often lack context necessary to make them understood, e.g., coreference and background information. To this end, we propose a content selection and planning framework for zero-shot decontextualisation, which determines what content should be mentioned and in what order for a sentence to be understood out of context. Specifically, given a potentially ambiguous sentence and its context, we first segment it into basic semantically-independent units. We then identify potentially ambiguous units from the given sentence, and extract relevant units from the context based on their discourse relations. Finally, we generate a content plan to rewrite the sentence by enriching each ambiguous unit with its relevant units. Experimental results demonstrate that our approach is competitive for sentence decontextualisation, producing sentences that exhibit better semantic integrity and discourse coherence, outperforming existing methods.

Paper Type: Long

Research Area: NLP Applications

Research Area Keywords: Decontextualisation;Discourse Analysis;Zero-shot Reasoning;Question Answering;Fact Checking

Contribution Types: Model analysis & interpretability, Data analysis

Languages Studied: English

Submission Number: 3360