Comparing Recurrent and Convolutional Architectures for English-Hindi Neural Machine Translation

Sandhya Singh, Ritesh Panjwani, Anoop Kunchukuttan, Pushpak Bhattacharyya


Abstract
In this paper, we empirically compare the two encoder-decoder neural machine translation architectures: convolutional sequence to sequence model (ConvS2S) and recurrent sequence to sequence model (RNNS2S) for English-Hindi language pair as part of IIT Bombay’s submission to WAT2017 shared task. We report the results for both English-Hindi and Hindi-English direction of language pair.
Anthology ID:
W17-5717
Volume:
Proceedings of the 4th Workshop on Asian Translation (WAT2017)
Month:
November
Year:
2017
Address:
Taipei, Taiwan
Editors:
Toshiaki Nakazawa, Isao Goto
Venue:
WAT
SIG:
Publisher:
Asian Federation of Natural Language Processing
Note:
Pages:
167–170
Language:
URL:
https://aclanthology.org/W17-5717
DOI:
Bibkey:
Cite (ACL):
Sandhya Singh, Ritesh Panjwani, Anoop Kunchukuttan, and Pushpak Bhattacharyya. 2017. Comparing Recurrent and Convolutional Architectures for English-Hindi Neural Machine Translation. In Proceedings of the 4th Workshop on Asian Translation (WAT2017), pages 167–170, Taipei, Taiwan. Asian Federation of Natural Language Processing.
Cite (Informal):
Comparing Recurrent and Convolutional Architectures for English-Hindi Neural Machine Translation (Singh et al., WAT 2017)
Copy Citation:
PDF:
https://aclanthology.org/W17-5717.pdf