Type

Conference Proceedings

Authors

Qun Liu
Andy Way
Hang Li
Xiaojun Zhang
Zhaopeng Tu
Longyue Wang

Subjects

Linguistics

Topics
training data neural networks machine translating parallel corpus machine translation source language target language deep learning

A Novel approach to dropped pronoun translation (2016)

Abstract Dropped Pronouns (DP) in which pronouns are frequently dropped in the source language but should be retained in the target language are challenge in machine translation. In response to this problem, we propose a semisupervised approach to recall possibly missing pronouns in the translation. Firstly, we build training data for DP generation in which the DPs are automatically labelled according to the alignment information from a parallel corpus. Secondly, we build a deep learning-based DP generator for input sentences in decoding when no corresponding references exist. More specifically, the generation is two-phase: (1) DP position detection, which is modeled as a sequential labelling task with recurrent neural networks; and (2) DP prediction, which employs a multilayer perceptron with rich features. Finally, we integrate the above outputs into our translation system to recall missing pronouns by both extracting rules from the DP-labelled training data and translating the DP-generated input sentences. Experimental results show that our approach achieves a significant improvement of 1.58 BLEU points in translation performance with 66% F-score for DP generation accuracy.
Collections Ireland -> Dublin City University -> Publication Type = Conference or Workshop Item
Ireland -> Dublin City University -> DCU Faculties and Centres = DCU Faculties and Schools: Faculty of Engineering and Computing: School of Computing
Ireland -> Dublin City University -> DCU Faculties and Centres = Research Initiatives and Centres: ADAPT
Ireland -> Dublin City University -> Status = Published
Ireland -> Dublin City University -> Subject = Computer Science: Machine translating

Full list of authors on original publication

Qun Liu, Andy Way, Hang Li, Xiaojun Zhang, Zhaopeng Tu, Longyue Wang

Experts in our system

1
Qun Liu
Dublin City University
Total Publications: 31
 
2
Andy Way
Dublin City University
Total Publications: 229
 
3
Zhaopeng Tu
Dublin City University
Total Publications: 6
 
4
Longyue Wang
Dublin City University
Total Publications: 8