Statistical machine translation based on translatio n rules
Yulian Hu · Journal of chemical and pharmaceutical research · 2014
Nowadays statistical machine translation shows its benefits and has received much attention. In this p aper, phrase-based statistical machine translation was ca refully studied. Improved Hidden Markov Model(HMM) was used to align words and solve the inconsistency bet ween word alignment and phrase structures, and can serve word alignment better. Translation rules were extracted based on aligned phrases and English phrase trees. CYK+, an improved CYK algorithm, as adopted as the decoder t o decode non-Chomsky translation rules; Two-round-decoding algorithm was proposed to integr ate the language model during decoding. The experim ent results showed the BLEU score of improved HMM was h igher than the score of HMM, so it follows that the translation system based on translation rules has m ore stable translation effect on different data col lection.