Learning to Jointly Translate and Predict Dropped Pronouns with a Shared Reconstruction Mechanism
This work addresses translation challenges for pro-drop languages, but it is incremental as it builds on prior reconstruction-based methods.
The paper tackled the problem of dropped pronoun translation in pro-drop languages like Chinese by improving a reconstruction-based neural machine translation model with a shared reconstructor and joint learning, resulting in significant improvements in both translation performance and DP prediction accuracy.
Pronouns are frequently omitted in pro-drop languages, such as Chinese, generally leading to significant challenges with respect to the production of complete translations. Recently, Wang et al. (2018) proposed a novel reconstruction-based approach to alleviating dropped pronoun (DP) translation problems for neural machine translation models. In this work, we improve the original model from two perspectives. First, we employ a shared reconstructor to better exploit encoder and decoder representations. Second, we jointly learn to translate and predict DPs in an end-to-end manner, to avoid the errors propagated from an external DP prediction model. Experimental results show that our approach significantly improves both translation performance and DP prediction accuracy.