Abstract
We present our submission to the IWSLT18 Low Resource task focused on the translation from Basque-to-English. Our submission is based on the current state-of-the-art self-attentive neural network architecture, Transformer. We further improve this strong baseline by exploiting available monolingual data using the back-translation technique. We also present further improvements gained by a transfer learning, a technique that trains a model using a high-resource language pair (Czech-English) and then fine-tunes the model using the target low-resource language pair (Basque-English).- Anthology ID:
- 2018.iwslt-1.21
- Volume:
- Proceedings of the 15th International Conference on Spoken Language Translation
- Month:
- October 29-30
- Year:
- 2018
- Address:
- Brussels
- Venue:
- IWSLT
- SIG:
- SIGSLT
- Publisher:
- International Conference on Spoken Language Translation
- Note:
- Pages:
- 142–146
- Language:
- URL:
- https://aclanthology.org/2018.iwslt-1.21
- DOI:
- Cite (ACL):
- Tom Kocmi, Dušan Variš, and Ondřej Bojar. 2018. CUNI Basque-to-English Submission in IWSLT18. In Proceedings of the 15th International Conference on Spoken Language Translation, pages 142–146, Brussels. International Conference on Spoken Language Translation.
- Cite (Informal):
- CUNI Basque-to-English Submission in IWSLT18 (Kocmi et al., IWSLT 2018)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/2018.iwslt-1.21.pdf