Hieu Pham


2018

pdf bib
SwitchOut: an Efficient Data Augmentation Algorithm for Neural Machine Translation
Xinyi Wang | Hieu Pham | Zihang Dai | Graham Neubig
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing

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 derive a generic analytic solution. This solution not only subsumes some existing augmentation schemes, but also leads to an extremely simple data augmentation strategy for NMT: randomly replacing words in both the source sentence and the target sentence with other random words from their corresponding vocabularies. We name this method SwitchOut. Experiments on three translation datasets of different scales show that SwitchOut yields consistent improvements of about 0.5 BLEU, achieving better or comparable performances to strong alternatives such as word dropout (Sennrich et al., 2016a). Code to implement this method is included in the appendix.

pdf bib
A Tree-based Decoder for Neural Machine Translation
Xinyi Wang | Hieu Pham | Pengcheng Yin | Graham Neubig
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing

Recent advances in Neural Machine Translation (NMT) show that adding syntactic information to NMT systems can improve the quality of their translations. Most existing work utilizes some specific types of linguistically-inspired tree structures, like constituency and dependency parse trees. This is often done via a standard RNN decoder that operates on a linearized target tree structure. However, it is an open question of what specific linguistic formalism, if any, is the best structural representation for NMT. In this paper, we (1) propose an NMT model that can naturally generate the topology of an arbitrary tree structure on the target side, and (2) experiment with various target tree structures. Our experiments show the surprising result that our model delivers the best improvements with balanced binary trees constructed without any linguistic knowledge; this model outperforms standard seq2seq models by up to 2.1 BLEU points, and other methods for incorporating target-side syntax by up to 0.7 BLEU.

2015

pdf bib
Effective Approaches to Attention-based Neural Machine Translation
Thang Luong | Hieu Pham | Christopher D. Manning
Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing

pdf bib
Learning Distributed Representations for Multilingual Text Sequences
Hieu Pham | Thang Luong | Christopher Manning
Proceedings of the 1st Workshop on Vector Space Modeling for Natural Language Processing

pdf bib
Bilingual Word Representations with Monolingual Quality in Mind
Thang Luong | Hieu Pham | Christopher D. Manning
Proceedings of the 1st Workshop on Vector Space Modeling for Natural Language Processing