Translating Pro-Drop Languages With Reconstruction Models

Authors

  • Longyue Wang ADAPT Centre, Dublin City University
  • Zhaopeng Tu Tencent AI Lab
  • Shuming Shi Tencent AI Lab
  • Tong Zhang Tencent AI Lab
  • Yvette Graham ADAPT Centre, Dublin City University
  • Qun Liu ADAPT Centre, Dublin City University

Keywords:

Neural Machine Translation, Pro-Drop Language, Dropped Pronoun, Reconstruction Model, Dialogue

Abstract

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 the 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.

Downloads

Published

2018-04-26

How to Cite

Wang, L., Tu, Z., Shi, S., Zhang, T., Graham, Y., & Liu, Q. (2018). Translating Pro-Drop Languages With Reconstruction Models. Proceedings of the AAAI Conference on Artificial Intelligence, 32(1). Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/11913

Issue

Section

Main Track: NLP and Knowledge Representation