Please use this identifier to cite or link to this item: doi:10.22028/D291-30982
Volltext verfügbar? / Dokumentlieferung
Title: A Systematic Study of Neural Discourse Models for Implicit Discourse Relation
Author(s): Rutherford, Attapol
Demberg, Vera
Xue, Nianwen
Editor(s): Kunnemann, Florian
Iñurrieta, Uxoa
Camilleri, John J.
Coll Ardanuy, Mariona
Language: English
Title: European Chapter of the Association for Computational Linguistics - proceedings of the Student Research Workshop
Startpage: 281
Endpage: 291
Publisher/Platform: ACL
Year of Publication: 2017
Place of publication: Stroudsburg, PA
Title of the Conference: EACL 2017
Place of the conference: Valencia, Spain
Publikation type: Conference Paper
Abstract: Inferring implicit discourse relations in natural language text is the most difficult subtask in discourse parsing. Many neural network models have been proposed to tackle this problem. However, the comparison for this task is not unified, so we could hardly draw clear conclusions about the effectiveness of various architectures. Here, we propose neural network models that are based on feedforward and long-short term memory architecture and systematically study the effects of varying structures. To our surprise, the best-configured feedforward architecture outperforms LSTM-based model in most cases despite thorough tuning. Further, we compare our best feedforward system with competitive convolutional and recurrent networks and find that feedforward can actually be more effective. For the first time for this task, we compile and publish outputs from previous neural and non-neural systems to establish the standard for further comparison.
DOI of the first publication: 10.18653/v1/E17-1027
URL of the first publication:
Link to this record: hdl:20.500.11880/29701
ISBN: 978-1-945626-37-1
Date of registration: 22-Sep-2020
Faculty: MI - Fakultät für Mathematik und Informatik
Department: MI - Informatik
Professorship: MI - Prof. Dr. Vera Demberg
Collections:UniBib – Die Universitätsbibliographie

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.