Please use this identifier to cite or link to this item:
Volltext verfügbar? / Dokumentlieferung
doi:10.22028/D291-30793
Title: | Using Explicit Discourse Connectives in Translation for Implicit Discourse Relation Classification |
Author(s): | Shi, Wei Yung, Frances Pikyu Rubino, Raphael Demberg, Vera |
Editor(s): | Kondrak, Greg Watanabe, Taro |
Language: | English |
Title: | The Eighth International Joint Conference on Natural Language Processing - proceedings of the conference : November 27-December 1, 2017, Taipei, Taiwan : IJCNLP 2017, Volume 1: Long Papers |
Startpage: | 484 |
Endpage: | 495 |
Publisher/Platform: | Association for Computational Linguistics |
Year of Publication: | 2017 |
Title of the Conference: | IJCNLP 2017 |
Place of the conference: | Taipei, Taiwan |
Publikation type: | Conference Paper |
Abstract: | Implicit discourse relation recognition is an extremely challenging task due to the lack of indicative connectives. Various neural network architectures have been proposed for this task recently, but most of them suffer from the shortage of labeled data. In this paper, we address this problem by procuring additional training data from parallel corpora: When humans translate a text, they sometimes add connectives (a process known as explicitation). We automatically back-translate it into an English connective and use it to infer a label with high confidence. We show that a training set several times larger than the original training set can be generated this way. With the extra labeled instances, we show that even a simple bidirectional Long Short-Term Memory Network can outperform the current state-of-the-art. |
URL of the first publication: | https://www.aclweb.org/anthology/I17-1049/ |
Link to this record: | hdl:20.500.11880/29714 http://dx.doi.org/10.22028/D291-30793 |
ISBN: | 978-1-948087-00-1 |
Date of registration: | 23-Sep-2020 |
Faculty: | MI - Fakultät für Mathematik und Informatik |
Department: | MI - Informatik |
Professorship: | MI - Prof. Dr. Vera Demberg |
Collections: | SciDok - Der Wissenschaftsserver der Universität des Saarlandes |
Files for this record:
There are no files associated with this item.
Items in SciDok are protected by copyright, with all rights reserved, unless otherwise indicated.