Multilingual Generative Language Models for Zero-Shot Cross-Lingual Event Argument Extraction

Kuan-Hao Huang, I-Hung Hsu, Prem Natarajan, Kai-Wei Chang, Nanyun Peng


Abstract
We present a study on leveraging multilingual pre-trained generative language models for zero-shot cross-lingual event argument extraction (EAE). By formulating EAE as a language generation task, our method effectively encodes event structures and captures the dependencies between arguments. We design language-agnostic templates to represent the event argument structures, which are compatible with any language, hence facilitating the cross-lingual transfer. Our proposed model finetunes multilingual pre-trained generative language models to generate sentences that fill in the language-agnostic template with arguments extracted from the input passage. The model is trained on source languages and is then directly applied to target languages for event argument extraction. Experiments demonstrate that the proposed model outperforms the current state-of-the-art models on zero-shot cross-lingual EAE. Comprehensive studies and error analyses are presented to better understand the advantages and the current limitations of using generative language models for zero-shot cross-lingual transfer EAE.
Anthology ID:
2022.acl-long.317
Volume:
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
May
Year:
2022
Address:
Dublin, Ireland
Editors:
Smaranda Muresan, Preslav Nakov, Aline Villavicencio
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
4633–4646
Language:
URL:
https://aclanthology.org/2022.acl-long.317
DOI:
10.18653/v1/2022.acl-long.317
Bibkey:
Cite (ACL):
Kuan-Hao Huang, I-Hung Hsu, Prem Natarajan, Kai-Wei Chang, and Nanyun Peng. 2022. Multilingual Generative Language Models for Zero-Shot Cross-Lingual Event Argument Extraction. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 4633–4646, Dublin, Ireland. Association for Computational Linguistics.
Cite (Informal):
Multilingual Generative Language Models for Zero-Shot Cross-Lingual Event Argument Extraction (Huang et al., ACL 2022)
Copy Citation:
PDF:
https://preview.aclanthology.org/naacl24-info/2022.acl-long.317.pdf
Software:
 2022.acl-long.317.software.zip
Video:
 https://preview.aclanthology.org/naacl24-info/2022.acl-long.317.mp4
Code
 pluslabnlp/x-gear