Abstract
This paper describes the University of Helsinki Language Technology group’s participation in the IWSLT 2020 offline speech translation task, addressing the translation of English audio into German text. In line with this year’s task objective, we train both cascade and end-to-end systems for spoken language translation. We opt for an end-to-end multitasking architecture with shared internal representations and a cascade approach that follows a standard procedure consisting of ASR, correction, and MT stages. We also describe the experiments that served as a basis for the submitted systems. Our experiments reveal that multitasking training with shared internal representations is not only possible but allows for knowledge-transfer across modalities.- Anthology ID:
- 2020.iwslt-1.10
- Volume:
- Proceedings of the 17th International Conference on Spoken Language Translation
- Month:
- July
- Year:
- 2020
- Address:
- Online
- Venue:
- IWSLT
- SIG:
- SIGSLT
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 95–102
- Language:
- URL:
- https://aclanthology.org/2020.iwslt-1.10
- DOI:
- 10.18653/v1/2020.iwslt-1.10
- Cite (ACL):
- Raúl Vázquez, Mikko Aulamo, Umut Sulubacak, and Jörg Tiedemann. 2020. The University of Helsinki Submission to the IWSLT2020 Offline SpeechTranslation Task. In Proceedings of the 17th International Conference on Spoken Language Translation, pages 95–102, Online. Association for Computational Linguistics.
- Cite (Informal):
- The University of Helsinki Submission to the IWSLT2020 Offline SpeechTranslation Task (Vázquez et al., IWSLT 2020)
- PDF:
- https://preview.aclanthology.org/remove-xml-comments/2020.iwslt-1.10.pdf