Introduction to the special issue on deep learning approaches for machine translation

Marta R. Costa-jussà, Alexandre Allauzen, Loïc Barrault, Kyunghyun Cho, Holger Schwenk

Research output: Contribution to journalArticle

Abstract

Deep learning is revolutionizing speech and natural language technologies since it is offering an effective way to train systems and obtaining significant improvements. The main advantage of deep learning is that, by developing the right architecture, the system automatically learns features from data without the need of explicitly designing them. This machine learning perspective is conceptually changing how speech and natural language technologies are addressed. In the case of Machine Translation (MT), deep learning was first introduced in standard statistical systems. By now, end-to-end neural MT systems have reached competitive results. This special issue introductory paper addresses how deep learning has been gradually introduced in MT. This introduction covers all topics contained in the papers included in this special issue, which basically are: integration of deep learning in statistical MT; development of the end-to-end neural MT system; and introduction of deep learning in interactive MT and MT evaluation. Finally, this introduction sketches some research directions that MT is taking guided by deep learning.

Original languageEnglish (US)
Pages (from-to)367-373
Number of pages7
JournalComputer Speech and Language
Volume46
DOIs
StatePublished - Nov 1 2017

Fingerprint

Machine Translation
Natural Language
Statistical Machine Translation
Learning
Deep learning
Learning systems
Machine Learning
Cover
Evaluation

Keywords

  • Deep learning
  • Machine translation

ASJC Scopus subject areas

  • Theoretical Computer Science
  • Software
  • Human-Computer Interaction

Cite this

Introduction to the special issue on deep learning approaches for machine translation. / Costa-jussà, Marta R.; Allauzen, Alexandre; Barrault, Loïc; Cho, Kyunghyun; Schwenk, Holger.

In: Computer Speech and Language, Vol. 46, 01.11.2017, p. 367-373.

Research output: Contribution to journalArticle

Costa-jussà, Marta R. ; Allauzen, Alexandre ; Barrault, Loïc ; Cho, Kyunghyun ; Schwenk, Holger. / Introduction to the special issue on deep learning approaches for machine translation. In: Computer Speech and Language. 2017 ; Vol. 46. pp. 367-373.
@article{211ad12334374770b73d457311965841,
title = "Introduction to the special issue on deep learning approaches for machine translation",
abstract = "Deep learning is revolutionizing speech and natural language technologies since it is offering an effective way to train systems and obtaining significant improvements. The main advantage of deep learning is that, by developing the right architecture, the system automatically learns features from data without the need of explicitly designing them. This machine learning perspective is conceptually changing how speech and natural language technologies are addressed. In the case of Machine Translation (MT), deep learning was first introduced in standard statistical systems. By now, end-to-end neural MT systems have reached competitive results. This special issue introductory paper addresses how deep learning has been gradually introduced in MT. This introduction covers all topics contained in the papers included in this special issue, which basically are: integration of deep learning in statistical MT; development of the end-to-end neural MT system; and introduction of deep learning in interactive MT and MT evaluation. Finally, this introduction sketches some research directions that MT is taking guided by deep learning.",
keywords = "Deep learning, Machine translation",
author = "Costa-juss{\`a}, {Marta R.} and Alexandre Allauzen and Lo{\"i}c Barrault and Kyunghyun Cho and Holger Schwenk",
year = "2017",
month = "11",
day = "1",
doi = "10.1016/j.csl.2017.03.001",
language = "English (US)",
volume = "46",
pages = "367--373",
journal = "Computer Speech and Language",
issn = "0885-2308",
publisher = "Academic Press Inc.",

}

TY - JOUR

T1 - Introduction to the special issue on deep learning approaches for machine translation

AU - Costa-jussà, Marta R.

AU - Allauzen, Alexandre

AU - Barrault, Loïc

AU - Cho, Kyunghyun

AU - Schwenk, Holger

PY - 2017/11/1

Y1 - 2017/11/1

N2 - Deep learning is revolutionizing speech and natural language technologies since it is offering an effective way to train systems and obtaining significant improvements. The main advantage of deep learning is that, by developing the right architecture, the system automatically learns features from data without the need of explicitly designing them. This machine learning perspective is conceptually changing how speech and natural language technologies are addressed. In the case of Machine Translation (MT), deep learning was first introduced in standard statistical systems. By now, end-to-end neural MT systems have reached competitive results. This special issue introductory paper addresses how deep learning has been gradually introduced in MT. This introduction covers all topics contained in the papers included in this special issue, which basically are: integration of deep learning in statistical MT; development of the end-to-end neural MT system; and introduction of deep learning in interactive MT and MT evaluation. Finally, this introduction sketches some research directions that MT is taking guided by deep learning.

AB - Deep learning is revolutionizing speech and natural language technologies since it is offering an effective way to train systems and obtaining significant improvements. The main advantage of deep learning is that, by developing the right architecture, the system automatically learns features from data without the need of explicitly designing them. This machine learning perspective is conceptually changing how speech and natural language technologies are addressed. In the case of Machine Translation (MT), deep learning was first introduced in standard statistical systems. By now, end-to-end neural MT systems have reached competitive results. This special issue introductory paper addresses how deep learning has been gradually introduced in MT. This introduction covers all topics contained in the papers included in this special issue, which basically are: integration of deep learning in statistical MT; development of the end-to-end neural MT system; and introduction of deep learning in interactive MT and MT evaluation. Finally, this introduction sketches some research directions that MT is taking guided by deep learning.

KW - Deep learning

KW - Machine translation

UR - http://www.scopus.com/inward/record.url?scp=85021932117&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85021932117&partnerID=8YFLogxK

U2 - 10.1016/j.csl.2017.03.001

DO - 10.1016/j.csl.2017.03.001

M3 - Article

AN - SCOPUS:85021932117

VL - 46

SP - 367

EP - 373

JO - Computer Speech and Language

JF - Computer Speech and Language

SN - 0885-2308

ER -