@article{garcia-romero-etal-2026-automatic,
title = "Automatic Machine Translation Detection Using a Surrogate Multilingual Translation Model",
author = "Garc{\'i}a-Romero, Cristian and
Espl{\`a}-Gomis, Miquel and
S{\'a}nchez-Mart{\'i}nez, Felipe",
journal = "Transactions of the Association for Computational Linguistics",
volume = "14",
year = "2026",
address = "Cambridge, MA",
publisher = "MIT Press",
url = "https://aclanthology.org/2026.tacl-1.55/",
doi = "10.1162/tacl.a.704",
pages = "1225--1242",
abstract = "Modern machine translation (MT) systems depend on large parallel corpora, often collected from the Internet. However, recent evidence indicates that (i) a substantial portion of these texts are machine-generated translations, and (ii) an overreliance on such synthetic content in training data can significantly degrade translation quality. As a result, filtering out non-human translations is becoming an essential pre-processing step in building high-quality MT systems. In this work, we propose a novel approach that directly exploits the internal representations of a surrogate multilingual MT model to distinguish between human and machine-translated sentences. Experimental results show that our method outperforms current state-of-the-art techniques, particularly for non-English language pairs, achieving gains of at least 5 percentage points of accuracy."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="garcia-romero-etal-2026-automatic">
<titleInfo>
<title>Automatic Machine Translation Detection Using a Surrogate Multilingual Translation Model</title>
</titleInfo>
<name type="personal">
<namePart type="given">Cristian</namePart>
<namePart type="family">García-Romero</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Miquel</namePart>
<namePart type="family">Esplà-Gomis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Felipe</namePart>
<namePart type="family">Sánchez-Martínez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026</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>Modern machine translation (MT) systems depend on large parallel corpora, often collected from the Internet. However, recent evidence indicates that (i) a substantial portion of these texts are machine-generated translations, and (ii) an overreliance on such synthetic content in training data can significantly degrade translation quality. As a result, filtering out non-human translations is becoming an essential pre-processing step in building high-quality MT systems. In this work, we propose a novel approach that directly exploits the internal representations of a surrogate multilingual MT model to distinguish between human and machine-translated sentences. Experimental results show that our method outperforms current state-of-the-art techniques, particularly for non-English language pairs, achieving gains of at least 5 percentage points of accuracy.</abstract>
<identifier type="citekey">garcia-romero-etal-2026-automatic</identifier>
<identifier type="doi">10.1162/tacl.a.704</identifier>
<location>
<url>https://aclanthology.org/2026.tacl-1.55/</url>
</location>
<part>
<date>2026</date>
<detail type="volume"><number>14</number></detail>
<extent unit="page">
<start>1225</start>
<end>1242</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Journal Article
%T Automatic Machine Translation Detection Using a Surrogate Multilingual Translation Model
%A García-Romero, Cristian
%A Esplà-Gomis, Miquel
%A Sánchez-Martínez, Felipe
%J Transactions of the Association for Computational Linguistics
%D 2026
%V 14
%I MIT Press
%C Cambridge, MA
%F garcia-romero-etal-2026-automatic
%X Modern machine translation (MT) systems depend on large parallel corpora, often collected from the Internet. However, recent evidence indicates that (i) a substantial portion of these texts are machine-generated translations, and (ii) an overreliance on such synthetic content in training data can significantly degrade translation quality. As a result, filtering out non-human translations is becoming an essential pre-processing step in building high-quality MT systems. In this work, we propose a novel approach that directly exploits the internal representations of a surrogate multilingual MT model to distinguish between human and machine-translated sentences. Experimental results show that our method outperforms current state-of-the-art techniques, particularly for non-English language pairs, achieving gains of at least 5 percentage points of accuracy.
%R 10.1162/tacl.a.704
%U https://aclanthology.org/2026.tacl-1.55/
%U https://doi.org/10.1162/tacl.a.704
%P 1225-1242
Markdown (Informal)
[Automatic Machine Translation Detection Using a Surrogate Multilingual Translation Model](https://aclanthology.org/2026.tacl-1.55/) (García-Romero et al., TACL 2026)
ACL