A Hybrid Machine Translation System Based on a Monotone Decoder

In this paper, a hybrid Machine Translation (MT) system is proposed by combining the result of a rule-based machine translation (RBMT) system with a statistical approach. The RBMT uses a set of linguistic rules for translation, which leads to better translation results in terms of word ordering and syntactic structure. On the other hand, SMT works better in lexical choice. Therefore, in our system, an initial translation is generated using RBMT. Then the proper lexical for the resulted sentence is chosen by using a decoder algorithm which is inspired by SMT architecture. In the pure SMT approach, decoder is responsible for selecting proper final lexical during the translation procedure. Normally this method deals with lexical choice as well as reordering and required exponential order in time complexity. By fixing the word order in the output, a polynomial version of this method, named monotone decoding, is used in this paper. Monotone decoder algorithm selects the best lexical from a candidate list by maximizing the language model of resulted sentence. The candidate list is gathered from the outputs of both pure RBMT and pure SMT systems.  The experiments of proposed hybrid method on English-Persian language pair show significant improvements over both RBMT and SMT results. The results show that the proposed hybrid method gains an improvement of almost +5 units over RBMT and about one unit over SMT in BLEU score.