In this paper, we have shown the improvement of English to Bharti Braille\nmachine translation system. We have shown how we can improve a baseline NMT\nmodel by adding some linguistic knowledge to it. This was done for five\nlanguage pairs where English sentences were translated into five Indian\nlanguages and then subsequently to corresponding Bharti Braille. This has been\ndemonstrated by adding a sub-module for translating multi-word expressions. The\napproach shows promising results as across language pairs, we could see\nimprovement in the quality of NMT outputs. The least improvement was observed\nin English-Nepali language pair with 22.08% and the most improvement was\nobserved in the English-Hindi language pair with 23.30%.\n
Linyu WeiMiao LiLei ChenZhenxin YangKai SunMan Yuan