This paper presents DeDisCo, Georgetown University's entry in the DISRPT 2025 shared task on discourse relation classification. We test two approaches, using an mt5-based encoder and a decoder based approach using the openly available Qwen model. We also experiment on training with augmented dataset for low-resource languages using matched data translated automatically from English, as well as using some additional linguistic features inspired by entries in previous editions of the Shared Task. Our system achieves a macro-accuracy score of 71.28, and we provide some interpretation and error analysis for our results.
@article{arxiv.2509.11498,
title = {DeDisCo at the DISRPT 2025 Shared Task: A System for Discourse Relation Classification},
author = {Zhuoxuan Ju and Jingni Wu and Abhishek Purushothama and Amir Zeldes},
journal= {arXiv preprint arXiv:2509.11498},
year = {2025}
}
Comments
System submission for the DISRPT 2025 - Shared Task on Discourse Relation Parsing and Treebanking In conjunction with CODI-CRAC & EMNLP 2025. 1st place in Task 3: relation classification