TY - JOUR
T1 - A survey on document-level neural machine translation
T2 - methods and evaluation
AU - Maruf, Sameen
AU - Saleh, Fahimeh
AU - Haffari, Gholamreza
N1 - Funding Information:
This work is supported by a Google Faculty Research Award and ARC FT190100039 to G.H. The authors are grateful to the anonymous reviewers for their valuable feedback and to George Foster for his comments on the final version of this paper. Authors’ addresses: S. Maruf, F. Saleh, and G. Haffari, Faculty of Information Technology, Monash University, Clayton, VIC, 3800, Australia; emails: {sameen.maruf, fahimeh.saleh, gholamreza.haffari}@monash.edu. Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]. © 2021 Copyright held by the owner/author(s). Publication rights licensed to ACM. 0360-0300/2021/03-ART45 $15.00 https://doi.org/10.1145/3441691
Publisher Copyright:
© 2021 ACM.
Copyright:
Copyright 2021 Elsevier B.V., All rights reserved.
PY - 2021/3
Y1 - 2021/3
N2 - Machine translation (MT) is an important task in natural language processing (NLP), as it automates the translation process and reduces the reliance on human translators. With the resurgence of neural networks, the translation quality surpasses that of the translations obtained using statistical techniques for most language-pairs. Up until a few years ago, almost all of the neural translation models translated sentences independently, without incorporating the wider document-context and inter-dependencies among the sentences. The aim of this survey article is to highlight the major works that have been undertaken in the space of document-level machine translation after the neural revolution, so researchers can recognize the current state and future directions of this field. We provide an organization of the literature based on novelties in modelling and architectures as well as training and decoding strategies. In addition, we cover evaluation strategies that have been introduced to account for the improvements in document MT, including automatic metrics and discourse-Targeted test sets. We conclude by presenting possible avenues for future exploration in this research field.
AB - Machine translation (MT) is an important task in natural language processing (NLP), as it automates the translation process and reduces the reliance on human translators. With the resurgence of neural networks, the translation quality surpasses that of the translations obtained using statistical techniques for most language-pairs. Up until a few years ago, almost all of the neural translation models translated sentences independently, without incorporating the wider document-context and inter-dependencies among the sentences. The aim of this survey article is to highlight the major works that have been undertaken in the space of document-level machine translation after the neural revolution, so researchers can recognize the current state and future directions of this field. We provide an organization of the literature based on novelties in modelling and architectures as well as training and decoding strategies. In addition, we cover evaluation strategies that have been introduced to account for the improvements in document MT, including automatic metrics and discourse-Targeted test sets. We conclude by presenting possible avenues for future exploration in this research field.
KW - Context-Aware neural machine translation
UR - http://www.scopus.com/inward/record.url?scp=85105765535&partnerID=8YFLogxK
U2 - 10.1145/3441691
DO - 10.1145/3441691
M3 - Review Article
AN - SCOPUS:85105765535
SN - 0360-0300
VL - 54
JO - ACM Computing Surveys
JF - ACM Computing Surveys
IS - 2
M1 - 45
ER -