Statistical Machine Translation for Indian Languages: Mission Hindi
This work addresses machine translation challenges for Indian languages, but it is incremental as it builds on existing SMT methods.
The paper tackled machine translation for Indian languages by proposing suffix separation and word splitting for agglutinative languages to Hindi, which improved over the baseline, and a factored model with reordering that outperformed phrase-based SMT for English-Hindi.
This paper discusses Centre for Development of Advanced Computing Mumbai's (CDACM) submission to the NLP Tools Contest on Statistical Machine Translation in Indian Languages (ILSMT) 2014 (collocated with ICON 2014). The objective of the contest was to explore the effectiveness of Statistical Machine Translation (SMT) for Indian language to Indian language and English-Hindi machine translation. In this paper, we have proposed that suffix separation and word splitting for SMT from agglutinative languages to Hindi significantly improves over the baseline (BL). We have also shown that the factored model with reordering outperforms the phrase-based SMT for English-Hindi (\enhi). We report our work on all five pairs of languages, namely Bengali-Hindi (\bnhi), Marathi-Hindi (\mrhi), Tamil-Hindi (\tahi), Telugu-Hindi (\tehi), and \enhi for Health, Tourism, and General domains.