A Unified Approach to Discourse Relation Classification in nine Languages

Hanna Varachkina, Franziska Pannach


Abstract
This paper presents efforts to solve the shared task on discourse relation classification (disrpt task 3). The intricate prediction task aims to predict a large number of classes from the Rhetorical Structure Theory (RST) framework for nine target languages. Labels include discourse relations such as background, condition, contrast and elaboration. We present an approach using euclidean distance between sentence embeddings that were extracted using multlingual sentence BERT (sBERT) and directionality as features. The data was combined into five classes which were used for initial prediction. The second classification step predicts the target classes. We observe a substantial difference in results depending on the number of occurrences of the target label in the training data. We achieve the best results on Chinese, where our system achieves 70 % accuracy on 20 labels.
Anthology ID:
2021.disrpt-1.5
Volume:
Proceedings of the 2nd Shared Task on Discourse Relation Parsing and Treebanking (DISRPT 2021)
Month:
November
Year:
2021
Address:
Punta Cana, Dominican Republic
Editors:
Amir Zeldes, Yang Janet Liu, Mikel Iruskieta, Philippe Muller, Chloé Braud, Sonia Badene
Venue:
DISRPT
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
46–50
Language:
URL:
https://aclanthology.org/2021.disrpt-1.5
DOI:
10.18653/v1/2021.disrpt-1.5
Bibkey:
Cite (ACL):
Hanna Varachkina and Franziska Pannach. 2021. A Unified Approach to Discourse Relation Classification in nine Languages. In Proceedings of the 2nd Shared Task on Discourse Relation Parsing and Treebanking (DISRPT 2021), pages 46–50, Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
A Unified Approach to Discourse Relation Classification in nine Languages (Varachkina & Pannach, DISRPT 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.disrpt-1.5.pdf