@inproceedings{goutte-etal-2012-impact,
title = "The Impact of Sentence Alignment Errors on Phrase-Based Machine Translation Performance",
author = "Goutte, Cyril and
Carpuat, Marine and
Foster, George",
booktitle = "Proceedings of the 10th Conference of the Association for Machine Translation in the Americas: Research Papers",
month = oct # " 28-" # nov # " 1",
year = "2012",
address = "San Diego, California, USA",
publisher = "Association for Machine Translation in the Americas",
url = "https://aclanthology.org/2012.amta-papers.7",
abstract = "When parallel or comparable corpora are harvested from the web, there is typically a tradeoff between the size and quality of the data. In order to improve quality, corpus collection efforts often attempt to fix or remove misaligned sentence pairs. But, at the same time, Statistical Machine Translation (SMT) systems are widely assumed to be relatively robust to sentence alignment errors. However, there is little empirical evidence to support and characterize this robustness. This contribution investigates the impact of sentence alignment errors on a typical phrase-based SMT system. We confirm that SMT systems are highly tolerant to noise, and that performance only degrades seriously at very high noise levels. Our findings suggest that when collecting larger, noisy parallel data for training phrase-based SMT, cleaning up by trying to detect and remove incorrect alignments can actually degrade performance. Although fixing errors, when applicable, is a preferable strategy to removal, its benefits only become apparent for fairly high misalignment rates. We provide several explanations to support these findings.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="goutte-etal-2012-impact">
<titleInfo>
<title>The Impact of Sentence Alignment Errors on Phrase-Based Machine Translation Performance</title>
</titleInfo>
<name type="personal">
<namePart type="given">Cyril</namePart>
<namePart type="family">Goutte</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marine</namePart>
<namePart type="family">Carpuat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">George</namePart>
<namePart type="family">Foster</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2012-oct 28-nov 1</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 10th Conference of the Association for Machine Translation in the Americas: Research Papers</title>
</titleInfo>
<originInfo>
<publisher>Association for Machine Translation in the Americas</publisher>
<place>
<placeTerm type="text">San Diego, California, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>When parallel or comparable corpora are harvested from the web, there is typically a tradeoff between the size and quality of the data. In order to improve quality, corpus collection efforts often attempt to fix or remove misaligned sentence pairs. But, at the same time, Statistical Machine Translation (SMT) systems are widely assumed to be relatively robust to sentence alignment errors. However, there is little empirical evidence to support and characterize this robustness. This contribution investigates the impact of sentence alignment errors on a typical phrase-based SMT system. We confirm that SMT systems are highly tolerant to noise, and that performance only degrades seriously at very high noise levels. Our findings suggest that when collecting larger, noisy parallel data for training phrase-based SMT, cleaning up by trying to detect and remove incorrect alignments can actually degrade performance. Although fixing errors, when applicable, is a preferable strategy to removal, its benefits only become apparent for fairly high misalignment rates. We provide several explanations to support these findings.</abstract>
<identifier type="citekey">goutte-etal-2012-impact</identifier>
<location>
<url>https://aclanthology.org/2012.amta-papers.7</url>
</location>
<part>
<date>2012-oct 28-nov 1</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The Impact of Sentence Alignment Errors on Phrase-Based Machine Translation Performance
%A Goutte, Cyril
%A Carpuat, Marine
%A Foster, George
%S Proceedings of the 10th Conference of the Association for Machine Translation in the Americas: Research Papers
%D 2012
%8 oct 28 nov 1
%I Association for Machine Translation in the Americas
%C San Diego, California, USA
%F goutte-etal-2012-impact
%X When parallel or comparable corpora are harvested from the web, there is typically a tradeoff between the size and quality of the data. In order to improve quality, corpus collection efforts often attempt to fix or remove misaligned sentence pairs. But, at the same time, Statistical Machine Translation (SMT) systems are widely assumed to be relatively robust to sentence alignment errors. However, there is little empirical evidence to support and characterize this robustness. This contribution investigates the impact of sentence alignment errors on a typical phrase-based SMT system. We confirm that SMT systems are highly tolerant to noise, and that performance only degrades seriously at very high noise levels. Our findings suggest that when collecting larger, noisy parallel data for training phrase-based SMT, cleaning up by trying to detect and remove incorrect alignments can actually degrade performance. Although fixing errors, when applicable, is a preferable strategy to removal, its benefits only become apparent for fairly high misalignment rates. We provide several explanations to support these findings.
%U https://aclanthology.org/2012.amta-papers.7
Markdown (Informal)
[The Impact of Sentence Alignment Errors on Phrase-Based Machine Translation Performance](https://aclanthology.org/2012.amta-papers.7) (Goutte et al., AMTA 2012)
ACL