Cross-lingual Intermediate Fine-tuning improves Dialogue State Tracking

Nikita Moghe, Mark Steedman, Alexandra Birch


Abstract
Recent progress in task-oriented neural dialogue systems is largely focused on a handful of languages, as annotation of training data is tedious and expensive. Machine translation has been used to make systems multilingual, but this can introduce a pipeline of errors. Another promising solution is using cross-lingual transfer learning through pretrained multilingual models. Existing methods train multilingual models with additional code-mixed task data or refine the cross-lingual representations through parallel ontologies. In this work, we enhance the transfer learning process by intermediate fine-tuning of pretrained multilingual models, where the multilingual models are fine-tuned with different but related data and/or tasks. Specifically, we use parallel and conversational movie subtitles datasets to design cross-lingual intermediate tasks suitable for downstream dialogue tasks. We use only 200K lines of parallel data for intermediate fine-tuning which is already available for 1782 language pairs. We test our approach on the cross-lingual dialogue state tracking task for the parallel MultiWoZ (English -> Chinese, Chinese -> English) and Multilingual WoZ (English -> German, English -> Italian) datasets. We achieve impressive improvements (> 20% on joint goal accuracy) on the parallel MultiWoZ dataset and the Multilingual WoZ dataset over the vanilla baseline with only 10% of the target language task data and zero-shot setup respectively.
Anthology ID:
2021.emnlp-main.87
Volume:
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2021
Address:
Online and Punta Cana, Dominican Republic
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1137–1150
Language:
URL:
https://aclanthology.org/2021.emnlp-main.87
DOI:
10.18653/v1/2021.emnlp-main.87
Bibkey:
Cite (ACL):
Nikita Moghe, Mark Steedman, and Alexandra Birch. 2021. Cross-lingual Intermediate Fine-tuning improves Dialogue State Tracking. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 1137–1150, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
Cross-lingual Intermediate Fine-tuning improves Dialogue State Tracking (Moghe et al., EMNLP 2021)
Copy Citation:
PDF:
https://preview.aclanthology.org/emnlp-22-attachments/2021.emnlp-main.87.pdf
Video:
 https://preview.aclanthology.org/emnlp-22-attachments/2021.emnlp-main.87.mp4
Code
 nikitacs16/xlift_dst
Data
OpenSubtitles