Abstract
Most of the existing discourse-level Information Extraction tasks have been modeled to be extractive in nature. However, we argue that extracting information from larger bodies of discourse-like documents requires more natural language understanding and reasoning capabilities. In our work, we propose the novel task of document-level event argument aggregation which generates consolidated event-arguments at a document-level with minimal loss of information. More specifically, we focus on generating precise document-level information frames in a multilingual setting using prompt-based methods. In this paper, we show the effectiveness of u prompt-based text generation approach to generate document-level argument spans in a low-resource and zero-shot setting. We also release the first of its kind multilingual event argument aggregation dataset that can be leveraged in other related multilingual text generation tasks as well: https://github.com/DebanjanaKar/ArgGen.- Anthology ID:
- 2022.findings-aacl.37
- Volume:
- Findings of the Association for Computational Linguistics: AACL-IJCNLP 2022
- Month:
- November
- Year:
- 2022
- Address:
- Online only
- Editors:
- Yulan He, Heng Ji, Sujian Li, Yang Liu, Chua-Hui Chang
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 399–404
- Language:
- URL:
- https://aclanthology.org/2022.findings-aacl.37
- DOI:
- Cite (ACL):
- Debanjana Kar, Sudeshna Sarkar, and Pawan Goyal. 2022. ArgGen: Prompting Text Generation Models for Document-Level Event-Argument Aggregation. In Findings of the Association for Computational Linguistics: AACL-IJCNLP 2022, pages 399–404, Online only. Association for Computational Linguistics.
- Cite (Informal):
- ArgGen: Prompting Text Generation Models for Document-Level Event-Argument Aggregation (Kar et al., Findings 2022)
- PDF:
- https://preview.aclanthology.org/cschoel_rss_and_blog/2022.findings-aacl.37.pdf