Abstract
Dialogue-level dependency parsing has received insufficient attention, especially for Chinese. To this end, we draw on ideas from syntactic dependency and rhetorical structure theory (RST), developing a high-quality human-annotated corpus, which contains 850 dialogues and 199,803 dependencies. Considering that such tasks suffer from high annotation costs, we investigate zero-shot and few-shot scenarios. Based on an existing syntactic treebank, we adopt a signal-based method to transform seen syntactic dependencies into unseen ones between elementary discourse units (EDUs), where the signals are detected by masked language modeling. Besides, we apply single-view and multi-view data selection to access reliable pseudo-labeled instances. Experimental results show the effectiveness of these baselines. Moreover, we discuss several crucial points about our dataset and approach.- Anthology ID:
- 2023.findings-acl.607
- Volume:
- Findings of the Association for Computational Linguistics: ACL 2023
- Month:
- July
- Year:
- 2023
- Address:
- Toronto, Canada
- Editors:
- Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 9526–9541
- Language:
- URL:
- https://aclanthology.org/2023.findings-acl.607
- DOI:
- 10.18653/v1/2023.findings-acl.607
- Cite (ACL):
- Gongyao Jiang, Shuang Liu, Meishan Zhang, and Min Zhang. 2023. A Pilot Study on Dialogue-Level Dependency Parsing for Chinese. In Findings of the Association for Computational Linguistics: ACL 2023, pages 9526–9541, Toronto, Canada. Association for Computational Linguistics.
- Cite (Informal):
- A Pilot Study on Dialogue-Level Dependency Parsing for Chinese (Jiang et al., Findings 2023)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-4/2023.findings-acl.607.pdf