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.

本研究提出了一种将传统SMT模型与神经机器翻译相结合的方法，从而提高翻译质量。该方法利用现有的基于短语的SMT模型计算基于短语的解码成本，并将其用于重新排列n个最佳NMT输出。研究表明，利用强制解码成本对NMT输出进行排序可以成功提高四种不同语言的翻译质量。

基于短语的强制解码改进神经机器翻译