Abstract
Transition systems have been widely used for the discourse dependency parsing task. Existing works often characterize transition states by examining a certain number of elementary discourse units (EDUs), while neglecting the arcs obtained from the transition history. In this paper, we propose to employ GAT-based encoder to learn dynamic representations for sub-trees constructed in previous transition steps. By incorporating these representations, our model is able to retain accessibility to all parsed EDUs through the obtained arcs, thus better utilizing the structural information of the document, particularly when handling lengthy text spans with complex structures. For the discourse relation recognition task, we employ edge-featured GATs to derive better representations for EDU pairs. Experimental results show that our model can achieve state-of-the-art performance on widely adopted datasets including RST-DT, SciDTB and CDTB. Our code is available at https://github.com/lty-lty/Discourse-Dependency-Parsing.- Anthology ID:
- 2023.findings-emnlp.951
- Volume:
- Findings of the Association for Computational Linguistics: EMNLP 2023
- Month:
- December
- Year:
- 2023
- Address:
- Singapore
- Editors:
- Houda Bouamor, Juan Pino, Kalika Bali
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 14253–14263
- Language:
- URL:
- https://aclanthology.org/2023.findings-emnlp.951
- DOI:
- 10.18653/v1/2023.findings-emnlp.951
- Cite (ACL):
- Tianyi Liu, Yansong Feng, and Dongyan Zhao. 2023. Learning Dynamic Representations for Discourse Dependency Parsing. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 14253–14263, Singapore. Association for Computational Linguistics.
- Cite (Informal):
- Learning Dynamic Representations for Discourse Dependency Parsing (Liu et al., Findings 2023)
- PDF:
- https://preview.aclanthology.org/emnlp-22-attachments/2023.findings-emnlp.951.pdf