Classification and Resolution of Non-Sentential Utterances in Dialogue

This article addresses the problems of classification and resolution of non-sentential utterances (NSUs) in dialogue. NSUs are utterances that do not have a complete sentential form but convey a full clausal meaning given the conversational context, such as “To the contrary!” or “How much?”. The pre...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Paolo Dragone, Pierre Lison
Formato:	article
Lenguaje:	EN
Publicado:	Accademia University Press 2016
Materias:	Social Sciences H Computational linguistics. Natural language processing P98-98.5
Acceso en línea:	https://doaj.org/article/e68d84582ad14b1bbcf84c1fb908c35f
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:e68d84582ad14b1bbcf84c1fb908c35f
record_format	dspace
spelling	oai:doaj.org-article:e68d84582ad14b1bbcf84c1fb908c35f2021-12-02T09:52:25ZClassification and Resolution of Non-Sentential Utterances in Dialogue2499-455310.4000/ijcol.353https://doaj.org/article/e68d84582ad14b1bbcf84c1fb908c35f2016-06-01T00:00:00Zhttp://journals.openedition.org/ijcol/353https://doaj.org/toc/2499-4553This article addresses the problems of classification and resolution of non-sentential utterances (NSUs) in dialogue. NSUs are utterances that do not have a complete sentential form but convey a full clausal meaning given the conversational context, such as “To the contrary!” or “How much?”. The presented approach builds upon the work of Fernández, Ginzburg, and Lappin (2007), who provide a taxonomy of NSUs divided in 15 classes along with a small annotated corpus extracted from dialogue transcripts. The main part of this article focuses on the automatic classification of NSUs according to these classes. We show that a combination of novel linguistic features and active learning techniques yields a significant improvement in the classification accuracy over the state-of-the-art, and is able to mitigate the scarcity of labelled data. Based on this classifier, the article also presents a novel approach for the semantic resolution of NSUs in context using probabilistic rules.Paolo DragonePierre LisonAccademia University PressarticleSocial SciencesHComputational linguistics. Natural language processingP98-98.5ENIJCoL, Vol 2, Iss 1, Pp 45-61 (2016)
institution	DOAJ
collection	DOAJ
language	EN
topic	Social Sciences H Computational linguistics. Natural language processing P98-98.5
spellingShingle	Social Sciences H Computational linguistics. Natural language processing P98-98.5 Paolo Dragone Pierre Lison Classification and Resolution of Non-Sentential Utterances in Dialogue
description	This article addresses the problems of classification and resolution of non-sentential utterances (NSUs) in dialogue. NSUs are utterances that do not have a complete sentential form but convey a full clausal meaning given the conversational context, such as “To the contrary!” or “How much?”. The presented approach builds upon the work of Fernández, Ginzburg, and Lappin (2007), who provide a taxonomy of NSUs divided in 15 classes along with a small annotated corpus extracted from dialogue transcripts. The main part of this article focuses on the automatic classification of NSUs according to these classes. We show that a combination of novel linguistic features and active learning techniques yields a significant improvement in the classification accuracy over the state-of-the-art, and is able to mitigate the scarcity of labelled data. Based on this classifier, the article also presents a novel approach for the semantic resolution of NSUs in context using probabilistic rules.
format	article
author	Paolo Dragone Pierre Lison
author_facet	Paolo Dragone Pierre Lison
author_sort	Paolo Dragone
title	Classification and Resolution of Non-Sentential Utterances in Dialogue
title_short	Classification and Resolution of Non-Sentential Utterances in Dialogue
title_full	Classification and Resolution of Non-Sentential Utterances in Dialogue
title_fullStr	Classification and Resolution of Non-Sentential Utterances in Dialogue
title_full_unstemmed	Classification and Resolution of Non-Sentential Utterances in Dialogue
title_sort	classification and resolution of non-sentential utterances in dialogue
publisher	Accademia University Press
publishDate	2016
url	https://doaj.org/article/e68d84582ad14b1bbcf84c1fb908c35f
work_keys_str_mv	AT paolodragone classificationandresolutionofnonsententialutterancesindialogue AT pierrelison classificationandresolutionofnonsententialutterancesindialogue
_version_	1718397978168786944

Classification and Resolution of Non-Sentential Utterances in Dialogue

Ejemplares similares