PRO-CS : An Instance-Based Prompt Composition Technique for Code-Switched Tasks

Srijan Bansal, Suraj Tripathi, Sumit Agarwal, Teruko Mitamura, Eric Nyberg

Abstract
Code-switched (CS) data is ubiquitous in today’s globalized world, but the dearth of annotated datasets in code-switching poses a significant challenge for learning diverse tasks across different language pairs. Parameter-efficient prompt-tuning approaches conditioned on frozen language models have shown promise for transfer learning in limited-resource setups. In this paper, we propose a novel instance-based prompt composition technique, PRO-CS, for CS tasks that combine language and task knowledge. We compare our approach with prompt-tuning and fine-tuning for code-switched tasks on 10 datasets across 4 language pairs. Our model outperforms the prompt-tuning approach by significant margins across all datasets and outperforms or remains at par with fine-tuning by using just 0.18% of total parameters. We also achieve competitive results when compared with the fine-tuned model in the low-resource cross-lingual and cross-task setting, indicating the effectiveness of our approach to incorporate new code-switched tasks.
Anthology ID:
2022.emnlp-main.698
Volume:
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates
Editors:
Yoav Goldberg, Zornitsa Kozareva, Yue Zhang
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
10243–10255
Language:
URL:
https://aclanthology.org/2022.emnlp-main.698
DOI:
10.18653/v1/2022.emnlp-main.698
Bibkey:
Cite (ACL):
Srijan Bansal, Suraj Tripathi, Sumit Agarwal, Teruko Mitamura, and Eric Nyberg. 2022. PRO-CS : An Instance-Based Prompt Composition Technique for Code-Switched Tasks. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 10243–10255, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
Cite (Informal):
PRO-CS : An Instance-Based Prompt Composition Technique for Code-Switched Tasks (Bansal et al., EMNLP 2022)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-4/2022.emnlp-main.698.pdf
PDF Search