Improving Zero-shot Sentence Decontextualisation with Content Selection and Planning

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Deng, Zhenyun, Chen, Yulong, Vlachos, Andreas
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866908595112640512
author Deng, Zhenyun
Chen, Yulong
Vlachos, Andreas
author_facet Deng, Zhenyun
Chen, Yulong
Vlachos, Andreas
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2509_17921
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Improving Zero-shot Sentence Decontextualisation with Content Selection and Planning
Deng, Zhenyun
Chen, Yulong
Vlachos, Andreas
Computation and Language
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.
title Improving Zero-shot Sentence Decontextualisation with Content Selection and Planning
topic Computation and Language
url https://arxiv.org/abs/2509.17921