Dropped pronoun generation for dialogue machine translation

Dropped pronoun (DP) is a common problem in dialogue machine translation, in which pronouns are frequently dropped in the source sentence and thus are missing in its translation. In response to this problem, we propose a novel approach to improve the translation of DPs for dialogue machine translation. Firstly, we build a training data for DP generation, in which the DPs are automatically added according to the alignment information from a parallel corpus. Then we model the DP generation problem as a sequence labelling task, and develop a generation model based on recurrent neural networks and language models. Finally, we apply the DP generator to machine translation task by completing the source sentences with the missing pronouns. Experimental results show that our approach achieves a significant improvement of 1.7 BLEU points by recalling possible DPs in the source sentences.