Hindi to English Machine Translation: Using Effective Selection in Multi-Model SMT

Kunal Sachdeva, Rishabh Srivastava, Sambhav Jain, Dipti Sharma


Abstract
Recent studies in machine translation support the fact that multi-model systems perform better than the individual models. In this paper, we describe a Hindi to English statistical machine translation system and improve over the baseline using multiple translation models. We have considered phrase based as well as hierarchical models and enhanced over both these baselines using a regression model. The system is trained over textual as well as syntactic features extracted from source and target of the aforementioned translations. Our system shows significant improvement over the baseline systems for both automatic as well as human evaluations. The proposed methodology is quite generic and easily be extended to other language pairs as well.
Anthology ID:
L14-1537
Volume:
Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14)
Month:
May
Year:
2014
Address:
Reykjavik, Iceland
Editors:
Nicoletta Calzolari, Khalid Choukri, Thierry Declerck, Hrafn Loftsson, Bente Maegaard, Joseph Mariani, Asuncion Moreno, Jan Odijk, Stelios Piperidis
Venue:
LREC
SIG:
Publisher:
European Language Resources Association (ELRA)
Note:
Pages:
1807–1811
Language:
URL:
http://www.lrec-conf.org/proceedings/lrec2014/pdf/682_Paper.pdf
DOI:
Bibkey:
Cite (ACL):
Kunal Sachdeva, Rishabh Srivastava, Sambhav Jain, and Dipti Sharma. 2014. Hindi to English Machine Translation: Using Effective Selection in Multi-Model SMT. In Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14), pages 1807–1811, Reykjavik, Iceland. European Language Resources Association (ELRA).
Cite (Informal):
Hindi to English Machine Translation: Using Effective Selection in Multi-Model SMT (Sachdeva et al., LREC 2014)
Copy Citation:
PDF:
http://www.lrec-conf.org/proceedings/lrec2014/pdf/682_Paper.pdf