Utilizing Lexical Similarity between Related, Low-resource Languages for Pivot-based SMT

Anoop Kunchukuttan, Maulik Shah, Pradyot Prakash, Pushpak Bhattacharyya


Abstract
We investigate pivot-based translation between related languages in a low resource, phrase-based SMT setting. We show that a subword-level pivot-based SMT model using a related pivot language is substantially better than word and morpheme-level pivot models. It is also highly competitive with the best direct translation model, which is encouraging as no direct source-target training corpus is used. We also show that combining multiple related language pivot models can rival a direct translation model. Thus, the use of subwords as translation units coupled with multiple related pivot languages can compensate for the lack of a direct parallel corpus.
Anthology ID:
I17-2048
Volume:
Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 2: Short Papers)
Month:
November
Year:
2017
Address:
Taipei, Taiwan
Editors:
Greg Kondrak, Taro Watanabe
Venue:
IJCNLP
SIG:
Publisher:
Asian Federation of Natural Language Processing
Note:
Pages:
283–289
Language:
URL:
https://aclanthology.org/I17-2048
DOI:
Bibkey:
Cite (ACL):
Anoop Kunchukuttan, Maulik Shah, Pradyot Prakash, and Pushpak Bhattacharyya. 2017. Utilizing Lexical Similarity between Related, Low-resource Languages for Pivot-based SMT. In Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 2: Short Papers), pages 283–289, Taipei, Taiwan. Asian Federation of Natural Language Processing.
Cite (Informal):
Utilizing Lexical Similarity between Related, Low-resource Languages for Pivot-based SMT (Kunchukuttan et al., IJCNLP 2017)
Copy Citation:
PDF:
https://aclanthology.org/I17-2048.pdf