@inproceedings{luong-etal-2016-neural,
title = "Neural Machine Translation",
author = "Luong, Thang and
Cho, Kyunghyun and
Manning, Christopher D.",
editor = "Birch, Alexandra and
Zuidema, Willem",
booktitle = "Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics: Tutorial Abstracts",
month = aug,
year = "2016",
address = "Berlin, Germany",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/P16-5005",
abstract = "Neural Machine Translation (NMT) is a simple new architecture for getting machines to learn to translate. Despite being relatively new (Kalchbrenner and Blunsom, 2013; Cho et al., 2014; Sutskever et al., 2014), NMT has already shown promising results, achieving state-of-the-art performances for various language pairs (Luong et al, 2015a; Jean et al, 2015; Luong et al, 2015b; Sennrich et al., 2016; Luong and Manning, 2016). While many of these NMT papers were presented to the ACL community, research and practice of NMT are only at their beginning stage. This tutorial would be a great opportunity for the whole community of machine translation and natural language processing to learn more about a very promising new approach to MT. This tutorial has four parts.In the first part, we start with an overview of MT approaches, including: (a) traditional methods that have been dominant over the past twenty years and (b) recent hybrid models with the use of neural network components. From these, we motivate why an end-to-end approach like neural machine translation is needed. The second part introduces a basic instance of NMT. We start out with a discussion of recurrent neural networks, including the back-propagation-through-time algorithm and stochastic gradient descent optimizers, as these are the foundation on which NMT builds. We then describe in detail the basic sequence-to-sequence architecture of NMT (Cho et al., 2014; Sutskever et al., 2014), the maximum likelihood training approach, and a simple beam-search decoder to produce translations.The third part of our tutorial describes techniques to build state-of-the-art NMT. We start with approaches to extend the vocabulary coverage of NMT (Luong et al., 2015a; Jean et al., 2015; Chitnis and DeNero, 2015). We then introduce the idea of jointly learning both translations and alignments through an attention mechanism (Bahdanau et al., 2015); other variants of attention (Luong et al., 2015b; Tu et al., 2016) are discussed too. We describe a recent trend in NMT, that is to translate at the sub-word level (Chung et al., 2016; Luong and Manning, 2016; Sennrich et al., 2016), so that language variations can be effectively handled. We then give tips on training and testing NMT systems such as batching and ensembling. In the final part of the tutorial, we briefly describe promising approaches, such as (a) how to combine multiple tasks to help translation (Dong et al., 2015; Luong et al., 2016; Firat et al., 2016; Zoph and Knight, 2016) and (b) how to utilize monolingual corpora (Sennrich et al., 2016). Lastly, we conclude with challenges remained to be solved for future NMT.PS: we would also like to acknowledge the very first paper by Forcada and {\~N}eco (1997) on sequence-to-sequence models for translation!",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="luong-etal-2016-neural">
<titleInfo>
<title>Neural Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Thang</namePart>
<namePart type="family">Luong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kyunghyun</namePart>
<namePart type="family">Cho</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="given">D</namePart>
<namePart type="family">Manning</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2016-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics: Tutorial Abstracts</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alexandra</namePart>
<namePart type="family">Birch</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Willem</namePart>
<namePart type="family">Zuidema</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Berlin, Germany</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Neural Machine Translation (NMT) is a simple new architecture for getting machines to learn to translate. Despite being relatively new (Kalchbrenner and Blunsom, 2013; Cho et al., 2014; Sutskever et al., 2014), NMT has already shown promising results, achieving state-of-the-art performances for various language pairs (Luong et al, 2015a; Jean et al, 2015; Luong et al, 2015b; Sennrich et al., 2016; Luong and Manning, 2016). While many of these NMT papers were presented to the ACL community, research and practice of NMT are only at their beginning stage. This tutorial would be a great opportunity for the whole community of machine translation and natural language processing to learn more about a very promising new approach to MT. This tutorial has four parts.In the first part, we start with an overview of MT approaches, including: (a) traditional methods that have been dominant over the past twenty years and (b) recent hybrid models with the use of neural network components. From these, we motivate why an end-to-end approach like neural machine translation is needed. The second part introduces a basic instance of NMT. We start out with a discussion of recurrent neural networks, including the back-propagation-through-time algorithm and stochastic gradient descent optimizers, as these are the foundation on which NMT builds. We then describe in detail the basic sequence-to-sequence architecture of NMT (Cho et al., 2014; Sutskever et al., 2014), the maximum likelihood training approach, and a simple beam-search decoder to produce translations.The third part of our tutorial describes techniques to build state-of-the-art NMT. We start with approaches to extend the vocabulary coverage of NMT (Luong et al., 2015a; Jean et al., 2015; Chitnis and DeNero, 2015). We then introduce the idea of jointly learning both translations and alignments through an attention mechanism (Bahdanau et al., 2015); other variants of attention (Luong et al., 2015b; Tu et al., 2016) are discussed too. We describe a recent trend in NMT, that is to translate at the sub-word level (Chung et al., 2016; Luong and Manning, 2016; Sennrich et al., 2016), so that language variations can be effectively handled. We then give tips on training and testing NMT systems such as batching and ensembling. In the final part of the tutorial, we briefly describe promising approaches, such as (a) how to combine multiple tasks to help translation (Dong et al., 2015; Luong et al., 2016; Firat et al., 2016; Zoph and Knight, 2016) and (b) how to utilize monolingual corpora (Sennrich et al., 2016). Lastly, we conclude with challenges remained to be solved for future NMT.PS: we would also like to acknowledge the very first paper by Forcada and Ñeco (1997) on sequence-to-sequence models for translation!</abstract>
<identifier type="citekey">luong-etal-2016-neural</identifier>
<location>
<url>https://aclanthology.org/P16-5005</url>
</location>
<part>
<date>2016-08</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Neural Machine Translation
%A Luong, Thang
%A Cho, Kyunghyun
%A Manning, Christopher D.
%Y Birch, Alexandra
%Y Zuidema, Willem
%S Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics: Tutorial Abstracts
%D 2016
%8 August
%I Association for Computational Linguistics
%C Berlin, Germany
%F luong-etal-2016-neural
%X Neural Machine Translation (NMT) is a simple new architecture for getting machines to learn to translate. Despite being relatively new (Kalchbrenner and Blunsom, 2013; Cho et al., 2014; Sutskever et al., 2014), NMT has already shown promising results, achieving state-of-the-art performances for various language pairs (Luong et al, 2015a; Jean et al, 2015; Luong et al, 2015b; Sennrich et al., 2016; Luong and Manning, 2016). While many of these NMT papers were presented to the ACL community, research and practice of NMT are only at their beginning stage. This tutorial would be a great opportunity for the whole community of machine translation and natural language processing to learn more about a very promising new approach to MT. This tutorial has four parts.In the first part, we start with an overview of MT approaches, including: (a) traditional methods that have been dominant over the past twenty years and (b) recent hybrid models with the use of neural network components. From these, we motivate why an end-to-end approach like neural machine translation is needed. The second part introduces a basic instance of NMT. We start out with a discussion of recurrent neural networks, including the back-propagation-through-time algorithm and stochastic gradient descent optimizers, as these are the foundation on which NMT builds. We then describe in detail the basic sequence-to-sequence architecture of NMT (Cho et al., 2014; Sutskever et al., 2014), the maximum likelihood training approach, and a simple beam-search decoder to produce translations.The third part of our tutorial describes techniques to build state-of-the-art NMT. We start with approaches to extend the vocabulary coverage of NMT (Luong et al., 2015a; Jean et al., 2015; Chitnis and DeNero, 2015). We then introduce the idea of jointly learning both translations and alignments through an attention mechanism (Bahdanau et al., 2015); other variants of attention (Luong et al., 2015b; Tu et al., 2016) are discussed too. We describe a recent trend in NMT, that is to translate at the sub-word level (Chung et al., 2016; Luong and Manning, 2016; Sennrich et al., 2016), so that language variations can be effectively handled. We then give tips on training and testing NMT systems such as batching and ensembling. In the final part of the tutorial, we briefly describe promising approaches, such as (a) how to combine multiple tasks to help translation (Dong et al., 2015; Luong et al., 2016; Firat et al., 2016; Zoph and Knight, 2016) and (b) how to utilize monolingual corpora (Sennrich et al., 2016). Lastly, we conclude with challenges remained to be solved for future NMT.PS: we would also like to acknowledge the very first paper by Forcada and Ñeco (1997) on sequence-to-sequence models for translation!
%U https://aclanthology.org/P16-5005
Markdown (Informal)
[Neural Machine Translation](https://aclanthology.org/P16-5005) (Luong et al., ACL 2016)
ACL
- Thang Luong, Kyunghyun Cho, and Christopher D. Manning. 2016. Neural Machine Translation. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics: Tutorial Abstracts, Berlin, Germany. Association for Computational Linguistics.