@article{luo-etal-2024-diverge,
title = "To Diverge or Not to Diverge: A Morphosyntactic Perspective on Machine Translation vs Human Translation",
author = "Luo, Jiaming and
Cherry, Colin and
Foster, George",
journal = "Transactions of the Association for Computational Linguistics",
volume = "12",
year = "2024",
address = "Cambridge, MA",
publisher = "MIT Press",
url = "https://aclanthology.org/2024.tacl-1.20",
doi = "10.1162/tacl_a_00645",
pages = "355--371",
abstract = "We conduct a large-scale fine-grained comparative analysis of machine translations (MTs) against human translations (HTs) through the lens of morphosyntactic divergence. Across three language pairs and two types of divergence defined as the structural difference between the source and the target, MT is consistently more conservative than HT, with less morphosyntactic diversity, more convergent patterns, and more one-to-one alignments. Through analysis on different decoding algorithms, we attribute this discrepancy to the use of beam search that biases MT towards more convergent patterns. This bias is most amplified when the convergent pattern appears around 50{\%} of the time in training data. Lastly, we show that for a majority of morphosyntactic divergences, their presence in HT is correlated with decreased MT performance, presenting a greater challenge for MT systems.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="luo-etal-2024-diverge">
<titleInfo>
<title>To Diverge or Not to Diverge: A Morphosyntactic Perspective on Machine Translation vs Human Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jiaming</namePart>
<namePart type="family">Luo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Colin</namePart>
<namePart type="family">Cherry</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>2024</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>We conduct a large-scale fine-grained comparative analysis of machine translations (MTs) against human translations (HTs) through the lens of morphosyntactic divergence. Across three language pairs and two types of divergence defined as the structural difference between the source and the target, MT is consistently more conservative than HT, with less morphosyntactic diversity, more convergent patterns, and more one-to-one alignments. Through analysis on different decoding algorithms, we attribute this discrepancy to the use of beam search that biases MT towards more convergent patterns. This bias is most amplified when the convergent pattern appears around 50% of the time in training data. Lastly, we show that for a majority of morphosyntactic divergences, their presence in HT is correlated with decreased MT performance, presenting a greater challenge for MT systems.</abstract>
<identifier type="citekey">luo-etal-2024-diverge</identifier>
<identifier type="doi">10.1162/tacl_a_00645</identifier>
<location>
<url>https://aclanthology.org/2024.tacl-1.20</url>
</location>
<part>
<date>2024</date>
<detail type="volume"><number>12</number></detail>
<extent unit="page">
<start>355</start>
<end>371</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Journal Article
%T To Diverge or Not to Diverge: A Morphosyntactic Perspective on Machine Translation vs Human Translation
%A Luo, Jiaming
%A Cherry, Colin
%A Foster, George
%J Transactions of the Association for Computational Linguistics
%D 2024
%V 12
%I MIT Press
%C Cambridge, MA
%F luo-etal-2024-diverge
%X We conduct a large-scale fine-grained comparative analysis of machine translations (MTs) against human translations (HTs) through the lens of morphosyntactic divergence. Across three language pairs and two types of divergence defined as the structural difference between the source and the target, MT is consistently more conservative than HT, with less morphosyntactic diversity, more convergent patterns, and more one-to-one alignments. Through analysis on different decoding algorithms, we attribute this discrepancy to the use of beam search that biases MT towards more convergent patterns. This bias is most amplified when the convergent pattern appears around 50% of the time in training data. Lastly, we show that for a majority of morphosyntactic divergences, their presence in HT is correlated with decreased MT performance, presenting a greater challenge for MT systems.
%R 10.1162/tacl_a_00645
%U https://aclanthology.org/2024.tacl-1.20
%U https://doi.org/10.1162/tacl_a_00645
%P 355-371
Markdown (Informal)
[To Diverge or Not to Diverge: A Morphosyntactic Perspective on Machine Translation vs Human Translation](https://aclanthology.org/2024.tacl-1.20) (Luo et al., TACL 2024)
ACL