Transitioning Representations between Languages for Cross-lingual Event Detection via Langevin Dynamics

Chien Nguyen, Huy Nguyen, Franck Dernoncourt, Thien Nguyen


Abstract
Cross-lingual transfer learning (CLTL) for event detection (ED) aims to develop models in high-resource source languages that can be directly applied to produce effective performance for lower-resource target languages. Previous research in this area has focused on representation matching methods to develop a language-universal representation space into which source- and target-language example representations can be mapped to achieve cross-lingual transfer. However, as this approach modifies the representations for the source-language examples, the models might lose discriminative features for ED that are learned over training data of the source language to prevent effective predictions. To this end, our work introduces a novel approach for cross-lingual ED where we only aim to transition the representations for the target-language examples into the source-language space, thus preserving the representations in the source language and their discriminative information. Our method introduces Langevin Dynamics to perform representation transition and a semantic preservation framework to retain event type features during the transition process. Extensive experiments over three languages demonstrate the state-of-the-art performance for ED in CLTL.
Anthology ID:
2023.findings-emnlp.938
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:
14085–14093
Language:
URL:
https://aclanthology.org/2023.findings-emnlp.938
DOI:
10.18653/v1/2023.findings-emnlp.938
Bibkey:
Cite (ACL):
Chien Nguyen, Huy Nguyen, Franck Dernoncourt, and Thien Nguyen. 2023. Transitioning Representations between Languages for Cross-lingual Event Detection via Langevin Dynamics. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 14085–14093, Singapore. Association for Computational Linguistics.
Cite (Informal):
Transitioning Representations between Languages for Cross-lingual Event Detection via Langevin Dynamics (Nguyen et al., Findings 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.findings-emnlp.938.pdf