T-Modules: Translation Modules for Zero-Shot Cross-Modal Machine Translation
Paul-Ambroise Duquenne, Hongyu Gong, Benoît Sagot, Holger Schwenk
Abstract
We present a new approach to perform zero-shot cross-modal transfer between speech and text for translation tasks. Multilingual speech and text are encoded in a joint fixed-size representation space. Then, we compare different approaches to decode these multimodal and multilingual fixed-size representations, enabling zero-shot translation between languages and modalities. All our models are trained without the need of cross-modal labeled translation data.Despite a fixed-size representation, we achieve very competitive results on several text and speech translation tasks. In particular, we significantly improve the state-of-the-art for zero-shot speech translation on Must-C. Incorporating a speech decoder in our framework, we introduce the first results for zero-shot direct speech-to-speech and text-to-speech translation.- Anthology ID:
- 2022.emnlp-main.391
- Volume:
- Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
- Month:
- December
- Year:
- 2022
- Address:
- Abu Dhabi, United Arab Emirates
- Venue:
- EMNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 5794–5806
- Language:
- URL:
- https://aclanthology.org/2022.emnlp-main.391
- DOI:
- Cite (ACL):
- Paul-Ambroise Duquenne, Hongyu Gong, Benoît Sagot, and Holger Schwenk. 2022. T-Modules: Translation Modules for Zero-Shot Cross-Modal Machine Translation. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 5794–5806, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
- Cite (Informal):
- T-Modules: Translation Modules for Zero-Shot Cross-Modal Machine Translation (Duquenne et al., EMNLP 2022)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/2022.emnlp-main.391.pdf