OATAO - Open Archive Toulouse Archive Ouverte Open Access Week

Learning Multi-party Discourse Structure Using Weak Supervision

Badene, Sonia and Thompson, Catherine and Lorré, Jean-Pierre and Asher, Nicholas Learning Multi-party Discourse Structure Using Weak Supervision. (2019) In: 25th International conference on computational linguistics and intellectual technologies (Dialogue 2019), 29 May 2019 - 1 June 2019 (Moscou, Russian Federation).

[img]
Preview
(Document in English)

PDF (Author's version) - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
412kB

Official URL: http://www.dialog-21.ru/media/4584/badenesplusetal-112.pdf

Abstract

Discourse structures provide a way to extract deep semantic information from text, e.g., about relations conveying causal and temporal information and topical organization, which can be gainfully employed in NLP tasks such as summarization, document classification, sentiment analysis. But the task of automatically learning discourse structures is difficult: the relations that make up the structures are very sparse relative to the number of possible semantic connections that could be made between any two segments within a text; furthermore, the existence of a relation between two segments depends not only on “local” features of the segments, but also on “global” contextual information, including which relations have already been instantiated in the text and where. It is natural to try to leverage the power of deep learning methods to learn the complex representations discourse structures require. However, deep learning methods demand a large amount of labeled data, which becomes prohibitively expensive in the case of expertly-annotated discourse corpora. One recent advance in the resolution of this “training data bottleneck”, data programming, allows for the implementation of expert knowledge in weak supervision system for data labeling. In this article, we present the results of our application of the data programming paradigm to the problem of discourse structure learning for multi-party dialogues.

Item Type:Conference or Workshop Item (Paper)
Additional Information:ISSN 2221-7932 http://www.dialog-21.ru/media/4584/badenesplusetal-112.pdf
HAL Id:hal-02365047
Audience (conference):International conference proceedings
Uncontrolled Keywords:
Institution:French research institutions > Centre National de la Recherche Scientifique - CNRS (FRANCE)
Université de Toulouse > Institut National Polytechnique de Toulouse - INPT (FRANCE)
Université de Toulouse > Université Toulouse III - Paul Sabatier - UT3 (FRANCE)
Université de Toulouse > Université Toulouse - Jean Jaurès - UT2J (FRANCE)
Université de Toulouse > Université Toulouse 1 Capitole - UT1 (FRANCE)
Other partners > Linagora (FRANCE)
Laboratory name:
Statistics:download
Deposited By: IRIT IRIT
Deposited On:14 Nov 2019 14:03

Repository Staff Only: item control page