Abstract
Implicit Discourse Relation Recognition (IDRR) involves identifying the sense label of an implicit connective between adjacent text spans. This has traditionally been approached as a classification task. However, some downstream tasks require more than just a sense label as well as the specific connective used. This paper presents Implicit Sense-labeled Connective Recognition (ISCR), which identifies the implicit connectives and their sense labels between adjacent text spans. ISCR can be treated as a classification task, but a large number of potential categories, sense labels, and uneven distribution of instances among them make this difficult. Instead, this paper handles the task as a text-generation task, using an encoder-decoder model to generate both connectives and their sense labels. Here, we explore a classification method and three kinds of text-generation methods. From our evaluation results on PDTB-3.0, we found that our method outperforms the conventional classification-based method.- Anthology ID:
- 2023.findings-emnlp.487
- 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:
- 7307–7313
- Language:
- URL:
- https://aclanthology.org/2023.findings-emnlp.487
- DOI:
- 10.18653/v1/2023.findings-emnlp.487
- Cite (ACL):
- Yui Oka and Tsutomu Hirao. 2023. Implicit Sense-labeled Connective Recognition as Text Generation. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 7307–7313, Singapore. Association for Computational Linguistics.
- Cite (Informal):
- Implicit Sense-labeled Connective Recognition as Text Generation (Oka & Hirao, Findings 2023)
- PDF:
- https://preview.aclanthology.org/emnlp-22-attachments/2023.findings-emnlp.487.pdf