@inproceedings{murray-chiang-2018-correcting,
title = "Correcting Length Bias in Neural Machine Translation",
author = "Murray, Kenton and
Chiang, David",
booktitle = "Proceedings of the Third Conference on Machine Translation: Research Papers",
month = oct,
year = "2018",
address = "Brussels, Belgium",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W18-6322",
doi = "10.18653/v1/W18-6322",
pages = "212--223",
abstract = "We study two problems in neural machine translation (NMT). First, in beam search, whereas a wider beam should in principle help translation, it often hurts NMT. Second, NMT has a tendency to produce translations that are too short. Here, we argue that these problems are closely related and both rooted in label bias. We show that correcting the brevity problem almost eliminates the beam problem; we compare some commonly-used methods for doing this, finding that a simple per-word reward works well; and we introduce a simple and quick way to tune this reward using the perceptron algorithm.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="murray-chiang-2018-correcting">
<titleInfo>
<title>Correcting Length Bias in Neural Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kenton</namePart>
<namePart type="family">Murray</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Chiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-oct</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Third Conference on Machine Translation: Research Papers</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Brussels, Belgium</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We study two problems in neural machine translation (NMT). First, in beam search, whereas a wider beam should in principle help translation, it often hurts NMT. Second, NMT has a tendency to produce translations that are too short. Here, we argue that these problems are closely related and both rooted in label bias. We show that correcting the brevity problem almost eliminates the beam problem; we compare some commonly-used methods for doing this, finding that a simple per-word reward works well; and we introduce a simple and quick way to tune this reward using the perceptron algorithm.</abstract>
<identifier type="citekey">murray-chiang-2018-correcting</identifier>
<identifier type="doi">10.18653/v1/W18-6322</identifier>
<location>
<url>https://aclanthology.org/W18-6322</url>
</location>
<part>
<date>2018-oct</date>
<extent unit="page">
<start>212</start>
<end>223</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Correcting Length Bias in Neural Machine Translation
%A Murray, Kenton
%A Chiang, David
%S Proceedings of the Third Conference on Machine Translation: Research Papers
%D 2018
%8 oct
%I Association for Computational Linguistics
%C Brussels, Belgium
%F murray-chiang-2018-correcting
%X We study two problems in neural machine translation (NMT). First, in beam search, whereas a wider beam should in principle help translation, it often hurts NMT. Second, NMT has a tendency to produce translations that are too short. Here, we argue that these problems are closely related and both rooted in label bias. We show that correcting the brevity problem almost eliminates the beam problem; we compare some commonly-used methods for doing this, finding that a simple per-word reward works well; and we introduce a simple and quick way to tune this reward using the perceptron algorithm.
%R 10.18653/v1/W18-6322
%U https://aclanthology.org/W18-6322
%U https://doi.org/10.18653/v1/W18-6322
%P 212-223
Markdown (Informal)
[Correcting Length Bias in Neural Machine Translation](https://aclanthology.org/W18-6322) (Murray & Chiang, 2018)
ACL