Going beyond zero-shot MT: combining phonological, morphological and semantic factors. The UdS-DFKI System at IWSLT 2017

Cristina España-Bonet, Josef van Genabith


Abstract
This paper describes the UdS-DFKI participation to the multilingual task of the IWSLT Evaluation 2017. Our approach is based on factored multilingual neural translation systems following the small data and zero-shot training conditions. Our systems are designed to fully exploit multilinguality by including factors that increase the number of common elements among languages such as phonetic coarse encodings and synsets, besides shallow part-of-speech tags, stems and lemmas. Document level information is also considered by including the topic of every document. This approach improves a baseline without any additional factor for all the language pairs and even allows beyond-zero-shot translation. That is, the translation from unseen languages is possible thanks to the common elements —especially synsets in our models— among languages.
Anthology ID:
2017.iwslt-1.2
Volume:
Proceedings of the 14th International Conference on Spoken Language Translation
Month:
December 14-15
Year:
2017
Address:
Tokyo, Japan
Editors:
Sakriani Sakti, Masao Utiyama
Venue:
IWSLT
SIG:
SIGSLT
Publisher:
International Workshop on Spoken Language Translation
Note:
Pages:
15–22
Language:
URL:
https://aclanthology.org/2017.iwslt-1.2
DOI:
Bibkey:
Cite (ACL):
Cristina España-Bonet and Josef van Genabith. 2017. Going beyond zero-shot MT: combining phonological, morphological and semantic factors. The UdS-DFKI System at IWSLT 2017. In Proceedings of the 14th International Conference on Spoken Language Translation, pages 15–22, Tokyo, Japan. International Workshop on Spoken Language Translation.
Cite (Informal):
Going beyond zero-shot MT: combining phonological, morphological and semantic factors. The UdS-DFKI System at IWSLT 2017 (España-Bonet & van Genabith, IWSLT 2017)
Copy Citation:
PDF:
https://preview.aclanthology.org/emnlp-22-attachments/2017.iwslt-1.2.pdf