@article{tu-etal-2018-learning,
title = "Learning to Remember Translation History with a Continuous Cache",
author = "Tu, Zhaopeng and
Liu, Yang and
Shi, Shuming and
Zhang, Tong",
editor = "Lee, Lillian and
Johnson, Mark and
Toutanova, Kristina and
Roark, Brian",
journal = "Transactions of the Association for Computational Linguistics",
volume = "6",
year = "2018",
address = "Cambridge, MA",
publisher = "MIT Press",
url = "https://aclanthology.org/Q18-1029",
doi = "10.1162/tacl_a_00029",
pages = "407--420",
abstract = "Existing neural machine translation (NMT) models generally translate sentences in isolation, missing the opportunity to take advantage of document-level information. In this work, we propose to augment NMT models with a very light-weight cache-like memory network, which stores recent hidden representations as translation history. The probability distribution over generated words is updated online depending on the translation history retrieved from the memory, endowing NMT models with the capability to dynamically adapt over time. Experiments on multiple domains with different topics and styles show the effectiveness of the proposed approach with negligible impact on the computational cost.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tu-etal-2018-learning">
<titleInfo>
<title>Learning to Remember Translation History with a Continuous Cache</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zhaopeng</namePart>
<namePart type="family">Tu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shuming</namePart>
<namePart type="family">Shi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tong</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<genre authority="bibutilsgt">journal article</genre>
<relatedItem type="host">
<titleInfo>
<title>Transactions of the Association for Computational Linguistics</title>
</titleInfo>
<originInfo>
<issuance>continuing</issuance>
<publisher>MIT Press</publisher>
<place>
<placeTerm type="text">Cambridge, MA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">periodical</genre>
<genre authority="bibutilsgt">academic journal</genre>
</relatedItem>
<abstract>Existing neural machine translation (NMT) models generally translate sentences in isolation, missing the opportunity to take advantage of document-level information. In this work, we propose to augment NMT models with a very light-weight cache-like memory network, which stores recent hidden representations as translation history. The probability distribution over generated words is updated online depending on the translation history retrieved from the memory, endowing NMT models with the capability to dynamically adapt over time. Experiments on multiple domains with different topics and styles show the effectiveness of the proposed approach with negligible impact on the computational cost.</abstract>
<identifier type="citekey">tu-etal-2018-learning</identifier>
<identifier type="doi">10.1162/tacl_a_00029</identifier>
<location>
<url>https://aclanthology.org/Q18-1029</url>
</location>
<part>
<date>2018</date>
<detail type="volume"><number>6</number></detail>
<extent unit="page">
<start>407</start>
<end>420</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Journal Article
%T Learning to Remember Translation History with a Continuous Cache
%A Tu, Zhaopeng
%A Liu, Yang
%A Shi, Shuming
%A Zhang, Tong
%J Transactions of the Association for Computational Linguistics
%D 2018
%V 6
%I MIT Press
%C Cambridge, MA
%F tu-etal-2018-learning
%X Existing neural machine translation (NMT) models generally translate sentences in isolation, missing the opportunity to take advantage of document-level information. In this work, we propose to augment NMT models with a very light-weight cache-like memory network, which stores recent hidden representations as translation history. The probability distribution over generated words is updated online depending on the translation history retrieved from the memory, endowing NMT models with the capability to dynamically adapt over time. Experiments on multiple domains with different topics and styles show the effectiveness of the proposed approach with negligible impact on the computational cost.
%R 10.1162/tacl_a_00029
%U https://aclanthology.org/Q18-1029
%U https://doi.org/10.1162/tacl_a_00029
%P 407-420
Markdown (Informal)
[Learning to Remember Translation History with a Continuous Cache](https://aclanthology.org/Q18-1029) (Tu et al., TACL 2018)
ACL