CrossAligner & Co: Zero-Shot Transfer Methods for Task-Oriented Cross-lingual Natural Language Understanding

Milan Gritta, Ruoyu Hu, Ignacio Iacobacci


Abstract
Task-oriented personal assistants enable people to interact with a host of devices and services using natural language. One of the challenges of making neural dialogue systems available to more users is the lack of training data for all but a few languages. Zero-shot methods try to solve this issue by acquiring task knowledge in a high-resource language such as English with the aim of transferring it to the low-resource language(s). To this end, we introduce CrossAligner, the principal method of a variety of effective approaches for zero-shot cross-lingual transfer based on learning alignment from unlabelled parallel data. We present a quantitative analysis of individual methods as well as their weighted combinations, several of which exceed state-of-the-art (SOTA) scores as evaluated across nine languages, fifteen test sets and three benchmark multilingual datasets. A detailed qualitative error analysis of the best methods shows that our fine-tuned language models can zero-shot transfer the task knowledge better than anticipated.
Anthology ID:
2022.findings-acl.319
Volume:
Findings of the Association for Computational Linguistics: ACL 2022
Month:
May
Year:
2022
Address:
Dublin, Ireland
Editors:
Smaranda Muresan, Preslav Nakov, Aline Villavicencio
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
4048–4061
Language:
URL:
https://aclanthology.org/2022.findings-acl.319
DOI:
10.18653/v1/2022.findings-acl.319
Bibkey:
Cite (ACL):
Milan Gritta, Ruoyu Hu, and Ignacio Iacobacci. 2022. CrossAligner & Co: Zero-Shot Transfer Methods for Task-Oriented Cross-lingual Natural Language Understanding. In Findings of the Association for Computational Linguistics: ACL 2022, pages 4048–4061, Dublin, Ireland. Association for Computational Linguistics.
Cite (Informal):
CrossAligner & Co: Zero-Shot Transfer Methods for Task-Oriented Cross-lingual Natural Language Understanding (Gritta et al., Findings 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.findings-acl.319.pdf
Code
 huawei-noah/noah-research
Data
MTOP