A Unified Approach to Discourse Relation Classification in nine Languages
2021 | conference paper. A publication with affiliation to the University of Göttingen.
Jump to: Cite & Linked | Documents & Media | Details | Version history
Cite this publication
A Unified Approach to Discourse Relation Classification in nine Languages
Varachkina, H. & Pannach, F. (2021)
Proceedings of the 2nd Shared Task on Discourse Relation Parsing and Treebanking (DISRPT 2021) pp. 46-50. 2nd Shared Task on Discourse Relation Parsing and Treebanking (DISRPT 2021), Punta Cana, Dominican Republic. DOI: https://doi.org/10.18653/v1/2021.disrpt-1.5
Documents & Media
Details
- Authors
- Varachkina, Hanna ; Pannach, Franziska
- 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.
- Issue Date
- 2021
- Organization
- Seminar für Deutsche Philologie ; Göttingen Centre for Digital Humanities
- Conference
- 2nd Shared Task on Discourse Relation Parsing and Treebanking (DISRPT 2021)
- Conference Place
- Punta Cana, Dominican Republic
- Event start
- 2021-11-11
- Event end
- 2021
- Language
- English