Compared to traditional statistical machine translation (SMT), neural machine translation (NMT) often sacrifices adequacy for the sake of fluency. We propose a method to combine the advantages of traditional SMT and NMT by exploiting an existing phrase-based SMT model to compute the phrase-based decoding cost for an NMT output and then using this cost to rerank the n-best NMT outputs. The main challenge in implementing this approach is that NMT outputs may not be in the search space of the standard phrase-based decoding algorithm, because the search space of phrase-based SMT is limited by the phrase-based translation rule table. We propose a soft forced decoding algorithm, which can always successfully find a decoding path for any NMT output. We show that using the forced decoding cost to rerank the NMT outputs can successfully improve translation quality on four different language pairs.
@article{arxiv.1711.00309,
title = {Improving Neural Machine Translation through Phrase-based Forced Decoding},
author = {Jingyi Zhang and Masao Utiyama and Eiichro Sumita and Graham Neubig and Satoshi Nakamura},
journal= {arXiv preprint arXiv:1711.00309},
year = {2017}
}