Pidong Wang


pdf bib
Multilingual Mix: Example Interpolation Improves Multilingual Neural Machine Translation
Yong Cheng | Ankur Bapna | Orhan Firat | Yuan Cao | Pidong Wang | Wolfgang Macherey
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Multilingual neural machine translation models are trained to maximize the likelihood of a mix of examples drawn from multiple language pairs. The dominant inductive bias applied to these models is a shared vocabulary and a shared set of parameters across languages; the inputs and labels corresponding to examples drawn from different language pairs might still reside in distinct sub-spaces. In this paper, we introduce multilingual crossover encoder-decoder (mXEncDec) to fuse language pairs at an instance level. Our approach interpolates instances from different language pairs into joint ‘crossover examples’ in order to encourage sharing input and output spaces across languages. To ensure better fusion of examples in multilingual settings, we propose several techniques to improve example interpolation across dissimilar languages under heavy data imbalance. Experiments on a large-scale WMT multilingual dataset demonstrate that our approach significantly improves quality on English-to-Many, Many-to-English and zero-shot translation tasks (from +0.5 BLEU up to +5.5 BLEU points). Results on code-switching sets demonstrate the capability of our approach to improve model generalization to out-of-distribution multilingual examples. We also conduct qualitative and quantitative representation comparisons to analyze the advantages of our approach at the representation level.


pdf bib
Source Language Adaptation Approaches for Resource-Poor Machine Translation
Pidong Wang | Preslav Nakov | Hwee Tou Ng
Computational Linguistics, Volume 42, Issue 2 - June 2016


pdf bib
Machine translation in mobile games: augmenting social media text normalization with incentivized feedback
Nikhil Bojja | Arun Nedunchezhian | Pidong Wang
Proceedings of Machine Translation Summit XV: User Track

pdf bib
A Language Detection System for Short Chats in Mobile Games
Pidong Wang | Nikhil Bojja | Shivasankari Kannan
Proceedings of the third International Workshop on Natural Language Processing for Social Media


pdf bib
A Beam-Search Decoder for Normalization of Social Media Text with Application to Machine Translation
Pidong Wang | Hwee Tou Ng
Proceedings of the 2013 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies


pdf bib
Source Language Adaptation for Resource-Poor Machine Translation
Pidong Wang | Preslav Nakov | Hwee Tou Ng
Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning