Hybrid Neural Network Alignment and Lexicon Model in Direct HMM for Statistical Machine Translation

Weiyue Wang, Tamer Alkhouli, Derui Zhu, Hermann Ney
2017 Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)  
Recently, the neural machine translation systems showed their promising performance and surpassed the phrase-based systems for most translation tasks. Retreating into conventional concepts machine translation while utilizing effective neural models is vital for comprehending the leap accomplished by neural machine translation over phrase-based methods. This work proposes a direct hidden Markov model (HMM) with neural network-based lexicon and alignment models, which are trained jointly using
more » ... ed jointly using the Baum-Welch algorithm. The direct HMM is applied to rerank the n-best list created by a state-of-the-art phrase-based translation system and it provides improvements by up to 1.0% BLEU scores on two different translation tasks.
doi:10.18653/v1/p17-2020 dblp:conf/acl/WangAZN17 fatcat:wjcewdqrkfcqjpz53ow3hcq7qe