Translating Pro-Drop Languages with Reconstruction Models
This work addresses a specific challenge in machine translation for pro-drop languages, offering an incremental improvement to enhance translation accuracy in dialogue contexts.
The paper tackles the dropped pronoun problem in neural machine translation for pro-drop languages like Chinese and Japanese, proposing a reconstruction-based approach that automatically annotates and embeds pronoun information, resulting in significant and consistent improvements over a strong baseline on Chinese-English and Japanese-English dialogue translation tasks.
Pronouns are frequently omitted in pro-drop languages, such as Chinese, generally leading to significant challenges with respect to the production of complete translations. To date, very little attention has been paid to the dropped pronoun (DP) problem within neural machine translation (NMT). In this work, we propose a novel reconstruction-based approach to alleviating DP translation problems for NMT models. Firstly, DPs within all source sentences are automatically annotated with parallel information extracted from the bilingual training corpus. Next, the annotated source sentence is reconstructed from hidden representations in the NMT model. With auxiliary training objectives, in terms of reconstruction scores, the parameters associated with the NMT model are guided to produce enhanced hidden representations that are encouraged as much as possible to embed annotated DP information. Experimental results on both Chinese-English and Japanese-English dialogue translation tasks show that the proposed approach significantly and consistently improves translation performance over a strong NMT baseline, which is directly built on the training data annotated with DPs.