DAMP: Doubly Aligned Multilingual Parser for Task-Oriented Dialogue

William Held, Christopher Hidey, Fei Liu, Eric Zhu, Rahul Goel, Diyi Yang, Rushin Shah


Abstract
Modern virtual assistants use internal semantic parsing engines to convert user utterances to actionable commands. However, prior work has demonstrated multilingual models are less robust for semantic parsing compared to other tasks. In global markets such as India and Latin America, robust multilingual semantic parsing is critical as codeswitching between languages is prevalent for bilingual users. In this work we dramatically improve the zero-shot performance of a multilingual and codeswitched semantic parsing system using two stages of multilingual alignment. First, we show that contrastive alignment pretraining improves both English performance and transfer efficiency. We then introduce a constrained optimization approach for hyperparameter-free adversarial alignment during finetuning. Our Doubly Aligned Multilingual Parser (DAMP) improves mBERT transfer performance by 3x, 6x, and 81x on the Spanglish, Hinglish and Multilingual Task Oriented Parsing benchmarks respectively and outperforms XLM-R and mT5-Large using 3.2x fewer parameters.
Anthology ID:
2023.acl-long.199
Volume:
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
July
Year:
2023
Address:
Toronto, Canada
Editors:
Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3586–3604
Language:
URL:
https://aclanthology.org/2023.acl-long.199
DOI:
10.18653/v1/2023.acl-long.199
Bibkey:
Cite (ACL):
William Held, Christopher Hidey, Fei Liu, Eric Zhu, Rahul Goel, Diyi Yang, and Rushin Shah. 2023. DAMP: Doubly Aligned Multilingual Parser for Task-Oriented Dialogue. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 3586–3604, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
DAMP: Doubly Aligned Multilingual Parser for Task-Oriented Dialogue (Held et al., ACL 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/naacl-24-ws-corrections/2023.acl-long.199.pdf
Video:
 https://preview.aclanthology.org/naacl-24-ws-corrections/2023.acl-long.199.mp4