A Discourse Coherence Analysis Method Combining Sentence Embedding and Dimension Grid

Discourse coherence is strongly associated with text quality, making it important to natural language generation and understanding. However, existing coherence models focus on measuring individual aspects of coherence, such as lexical overlap, entity centralization, rhetorical structure, etc., lacki...

Description complète

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Lanlan Jiang, Shengjun Yuan, Jun Li
Format:	article
Langue:	EN
Publié:	Hindawi-Wiley 2021
Sujets:	Electronic computers. Computer science QA75.5-76.95
Accès en ligne:	https://doaj.org/article/50980c0e8a68459093f46e6c3bca8eac
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

id	oai:doaj.org-article:50980c0e8a68459093f46e6c3bca8eac
record_format	dspace
spelling	oai:doaj.org-article:50980c0e8a68459093f46e6c3bca8eac2021-11-15T01:19:54ZA Discourse Coherence Analysis Method Combining Sentence Embedding and Dimension Grid1099-052610.1155/2021/6654925https://doaj.org/article/50980c0e8a68459093f46e6c3bca8eac2021-01-01T00:00:00Zhttp://dx.doi.org/10.1155/2021/6654925https://doaj.org/toc/1099-0526Discourse coherence is strongly associated with text quality, making it important to natural language generation and understanding. However, existing coherence models focus on measuring individual aspects of coherence, such as lexical overlap, entity centralization, rhetorical structure, etc., lacking measurement of the semantics of text. In this paper, we propose a discourse coherence analysis method combining sentence embedding and the dimension grid, we obtain sentence-level vector representation by deep learning, and we introduce a coherence model that captures the fine-grained semantic transitions in text. Our work is based on the hypothesis that each dimension in the embedding vector is exactly assigned a stated certainty and specific semantic. We take every dimension as an equal grid and compute its transition probabilities. The document feature vector is also enriched to model the coherence. Finally, the experimental results demonstrate that our method achieves excellent performance on two coherence-related tasks.Lanlan JiangShengjun YuanJun LiHindawi-WileyarticleElectronic computers. Computer scienceQA75.5-76.95ENComplexity, Vol 2021 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Electronic computers. Computer science QA75.5-76.95
spellingShingle	Electronic computers. Computer science QA75.5-76.95 Lanlan Jiang Shengjun Yuan Jun Li A Discourse Coherence Analysis Method Combining Sentence Embedding and Dimension Grid
description	Discourse coherence is strongly associated with text quality, making it important to natural language generation and understanding. However, existing coherence models focus on measuring individual aspects of coherence, such as lexical overlap, entity centralization, rhetorical structure, etc., lacking measurement of the semantics of text. In this paper, we propose a discourse coherence analysis method combining sentence embedding and the dimension grid, we obtain sentence-level vector representation by deep learning, and we introduce a coherence model that captures the fine-grained semantic transitions in text. Our work is based on the hypothesis that each dimension in the embedding vector is exactly assigned a stated certainty and specific semantic. We take every dimension as an equal grid and compute its transition probabilities. The document feature vector is also enriched to model the coherence. Finally, the experimental results demonstrate that our method achieves excellent performance on two coherence-related tasks.
format	article
author	Lanlan Jiang Shengjun Yuan Jun Li
author_facet	Lanlan Jiang Shengjun Yuan Jun Li
author_sort	Lanlan Jiang
title	A Discourse Coherence Analysis Method Combining Sentence Embedding and Dimension Grid
title_short	A Discourse Coherence Analysis Method Combining Sentence Embedding and Dimension Grid
title_full	A Discourse Coherence Analysis Method Combining Sentence Embedding and Dimension Grid
title_fullStr	A Discourse Coherence Analysis Method Combining Sentence Embedding and Dimension Grid
title_full_unstemmed	A Discourse Coherence Analysis Method Combining Sentence Embedding and Dimension Grid
title_sort	discourse coherence analysis method combining sentence embedding and dimension grid
publisher	Hindawi-Wiley
publishDate	2021
url	https://doaj.org/article/50980c0e8a68459093f46e6c3bca8eac
work_keys_str_mv	AT lanlanjiang adiscoursecoherenceanalysismethodcombiningsentenceembeddinganddimensiongrid AT shengjunyuan adiscoursecoherenceanalysismethodcombiningsentenceembeddinganddimensiongrid AT junli adiscoursecoherenceanalysismethodcombiningsentenceembeddinganddimensiongrid AT lanlanjiang discoursecoherenceanalysismethodcombiningsentenceembeddinganddimensiongrid AT shengjunyuan discoursecoherenceanalysismethodcombiningsentenceembeddinganddimensiongrid AT junli discoursecoherenceanalysismethodcombiningsentenceembeddinganddimensiongrid
_version_	1718428921494503424

A Discourse Coherence Analysis Method Combining Sentence Embedding and Dimension Grid

Documents similaires