Please use this identifier to cite or link to this item: doi:10.22028/D291-30792
Volltext verfügbar? / Dokumentlieferung
Title: Learning to Explicitate Connectives with Seq2Seq Network for Implicit Discourse Relation Classification
Author(s): Shi, Wei
Demberg, Vera
Editor(s): Dobnik, Simon
Language: English
Title: Proceedings of the 13th International Conference on Computational Semantics - long papers
Startpage: 188
Endpage: 199
Publisher/Platform: ACL
Year of Publication: 2019
Place of publication: Stroudsburg, PA
Title of the Conference: IWCS 2019
Place of the conference: Gothenburg, Sweden
Publikation type: Conference Paper
Abstract: Implicit discourse relation classification is one of the most difficult steps in discourse parsing. The difficulty stems from the fact that the coherence relation must be inferred based on the content of the discourse relational arguments. Therefore, an effective encoding of the relational arguments is of crucial importance. We here propose a new model for implicit discourse relation classification, which consists of a classifier, and a sequence-to-sequence model which is trained to generate a representation of the discourse relational arguments by trying to predict the relational arguments including a suitable implicit connective. Training is possible because such implicit connectives have been annotated as part of the PDTB corpus. Along with a memory network, our model could generate more refined representations for the task. And on the now standard 11-way classification, our method outperforms the previous state of the art systems on the PDTB benchmark on multiple settings including cross validation.
DOI of the first publication: 10.18653/v1/W19-0416
URL of the first publication:
Link to this record: hdl:20.500.11880/29706
ISBN: 978-1-950737-19-2
Date of registration: 23-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.