Translating Short Segments with NMT: A Case Study in English-to-Hindi

Shantipriya Parida, Ondřej Bojar


Abstract
This paper presents a case study in translating short image captions of the Visual Genome dataset from English into Hindi using out-of-domain data sets of varying size. We experiment with three NMT models: the shallow and deep sequence-tosequence and the Transformer model as implemented in Marian toolkit. Phrase-based Moses serves as the baseline. The results indicate that the Transformer model outperforms others in the large data setting in a number of automatic metrics and manual evaluation, and it also produces the fewest truncated sentences. Transformer training is however very sensitive to the hyperparameters, so it requires more experimenting. The deep sequence-to-sequence model produced more flawless outputs in the small data setting and it was generally more stable, at the cost of more training iterations.
Anthology ID:
2018.eamt-main.23
Volume:
Proceedings of the 21st Annual Conference of the European Association for Machine Translation
Month:
May
Year:
2018
Address:
Alicante, Spain
Editors:
Juan Antonio Pérez-Ortiz, Felipe Sánchez-Martínez, Miquel Esplà-Gomis, Maja Popović, Celia Rico, André Martins, Joachim Van den Bogaert, Mikel L. Forcada
Venue:
EAMT
SIG:
Publisher:
Note:
Pages:
249–258
Language:
URL:
https://aclanthology.org/2018.eamt-main.23
DOI:
Bibkey:
Cite (ACL):
Shantipriya Parida and Ondřej Bojar. 2018. Translating Short Segments with NMT: A Case Study in English-to-Hindi. In Proceedings of the 21st Annual Conference of the European Association for Machine Translation, pages 249–258, Alicante, Spain.
Cite (Informal):
Translating Short Segments with NMT: A Case Study in English-to-Hindi (Parida & Bojar, EAMT 2018)
Copy Citation:
PDF:
https://aclanthology.org/2018.eamt-main.23.pdf