Please use this identifier to cite or link to this item:
Volltext verfügbar? / Dokumentlieferung
doi:10.22028/D291-30791
Title: | Next Sentence Prediction helps Implicit Discourse Relation Classification within and across Domains |
Author(s): | Shi, Wei Demberg, Vera |
Editor(s): | Inui, Kentaro |
Language: | English |
Title: | 2019 Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing - proceedings of the conference : November 3-7, 2019, Hong Kong, China : EMNLP-IJCNLP 2019 |
Startpage: | 5790 |
Endpage: | 5796 |
Publisher/Platform: | ACL |
Year of Publication: | 2019 |
Place of publication: | Stroudsburg, PA |
Title of the Conference: | EMNLP-IJCNLP 2019 |
Place of the conference: | Hong Kong, China |
Publikation type: | Conference Paper |
Abstract: | Implicit discourse relation classification is one of the most difficult tasks in discourse parsing. Previous studies have generally focused on extracting better representations of the relational arguments. In order to solve the task, it is however additionally necessary to capture what events are expected to cause or follow each other. Current discourse relation classifiers fall short in this respect. We here show that this shortcoming can be effectively addressed by using the bidirectional encoder representation from transformers (BERT) proposed by Devlin et al. (2019), which were trained on a next-sentence prediction task, and thus encode a representation of likely next sentences. The BERT-based model outperforms the current state of the art in 11-way classification by 8% points on the standard PDTB dataset. Our experiments also demonstrate that the model can be successfully ported to other domains: on the BioDRB dataset, the model outperforms the state of the art system around 15% points. |
DOI of the first publication: | 10.18653/v1/D19-1586 |
URL of the first publication: | https://www.aclweb.org/anthology/D19-1586/ |
Link to this record: | hdl:20.500.11880/29705 http://dx.doi.org/10.22028/D291-30791 |
ISBN: | 978-1-950737-90-1 |
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.