Abstract
Task-oriented Dialogue (ToD) agents are mostly limited to a few widely-spoken languages, mainly due to the high cost of acquiring training data for each language. Existing low-cost approaches that rely on cross-lingual embeddings or naive machine translation sacrifice a lot of accuracy for data efficiency, and largely fail in creating a usable dialogue agent. We propose automatic methods that use ToD training data in a source language to build a high-quality functioning dialogue agent in another target language that has no training data (i.e. zero-shot) or a small training set (i.e. few-shot). Unlike most prior work in cross-lingual ToD that only focuses on Dialogue State Tracking (DST), we build an end-to-end agent. We show that our approach closes the accuracy gap between few-shot and existing full-shot methods for ToD agents. We achieve this by (1) improving the dialogue data representation, (2) improving entity-aware machine translation, and (3) automatic filtering of noisy translations. We evaluate our approach on the recent bilingual dialogue dataset BiToD.In Chinese to English transfer, in the zero-shot setting, our method achieves 46.7% and 22.0% in Task Success Rate (TSR) and Dialogue Success Rate (DSR) respectively. In the few-shot setting where 10% of the data in the target language is used, we improve the state-of-the-art by 15.2% and 14.0%, coming within 5% of full-shot training.- Anthology ID:
- 2023.eacl-main.62
- Volume:
- Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics
- Month:
- May
- Year:
- 2023
- Address:
- Dubrovnik, Croatia
- Editors:
- Andreas Vlachos, Isabelle Augenstein
- Venue:
- EACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 886–901
- Language:
- URL:
- https://aclanthology.org/2023.eacl-main.62
- DOI:
- 10.18653/v1/2023.eacl-main.62
- Cite (ACL):
- Mehrad Moradshahi, Sina Semnani, and Monica Lam. 2023. Zero and Few-Shot Localization of Task-Oriented Dialogue Agents with a Distilled Representation. In Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, pages 886–901, Dubrovnik, Croatia. Association for Computational Linguistics.
- Cite (Informal):
- Zero and Few-Shot Localization of Task-Oriented Dialogue Agents with a Distilled Representation (Moradshahi et al., EACL 2023)
- PDF:
- https://preview.aclanthology.org/revert-3132-ingestion-checklist/2023.eacl-main.62.pdf