Hieu Pham

Multilingual Neural Machine Translation With Soft Decoupled Encoding

2019 · arXiv (Cornell University)

Multilingual training of neural machine translation (NMT) systems has led to impressive accuracy improvements on low-resource languages. However, there are still significant challenges in efficiently learning word representations in the face of paucity of data. …

Effective Approaches to Attention-based Neural Machine Translation

2015 · arXiv (Cornell University)

An attentional mechanism has lately been used to improve neural machine translation (NMT) by selectively focusing on parts of the source sentence during translation. However, there has been little work exploring useful architectures for attention-based …

Bilingual Word Representations with Monolingual Quality in Mind

2015

Recent work in learning bilingual representations tend to tailor towards achieving good performance on bilingual tasks, most often the crosslingual document classification (CLDC) evaluation, but to the detriment of preserving clustering structures of word representations …

Learning Distributed Representations for Multilingual Text Sequences

2015

We propose a novel approach to learning dis-tributed representations of variable-length text sequences in multiple languages simultane-ously. Unlike previous work which often de-rive representations of multi-word sequences as weighted sums of individual word vec-tors, our …

SwitchOut: an Efficient Data Augmentation Algorithm for Neural Machine Translation

2018

In this work, we examine methods for data augmentation for text-based tasks such as neural machine translation (NMT). We formulate the design of a data augmentation policy with desirable properties as an optimization problem, and …