@inproceedings{mash-etal-2026-alignment,
title = "Alignment Quality Degradation Across the Parallel{--}Comparable Spectrum: A Comparative Analysis",
author = "Mash, Audrey and
Orama, Jonathan Ayebakuro and
Garcia, Marc Juvill{\`a} and
Melero, Maite",
editor = "Shterionov, Dimitar and
Vanmassenhove, Eva and
De Sisto, Mirella and
Blain, Fred and
Pourmostafa Roshan Sharami, Javad and
Lepp, Lisa and
Manna, Chiara and
Rescigno, Argentina Anna and
Karakanta, Alina and
Rigouts Terryn, Ayla and
Lardelli, Manuel and
Resende, Natalia and
Murgolo, Elena and
Hackenbuchner, Jani{\c{c}}a and
Zaretskaya, Anna and
Espl{\`a}-Gomis, Miquel and
Etchegoyhen, Thierry and
Gromann, Dagmar and
Bawden, Rachel and
Haddow, Barry and
Szoc, Sara and
Forcada, Mikel and
Moniz, Helena",
booktitle = "Proceedings of the 26th Annual Conference of the {E}uropean Association for Machine Translation (Volume 1)",
month = jun,
year = "2026",
address = "Tilburg, The Netherlands",
publisher = "European Association for Machine Translation",
url = "https://aclanthology.org/2026.eamt-1.11/",
pages = "130--142",
ISBN = "9789403901411",
abstract = "Sentence-level alignment systems have been developed and evaluated primarily on parallel data, leaving their behaviour across the broader parallel-comparable spectrum of real web content poorly understood. We present a stratified empirical study of alignment quality for Catalan-English using 300 document pairs across three parallelism bands defined by mean-max LaBSE cosine similarity. We compare four systems: a hierarchical alignment pipeline (DocAlign), an ablation with paragraph pre-filtering disabled (DocAlign-NoFilter), the flat aligner Vecalign, and a flat LaBSE greedy baseline. Evaluation uses human-annotated sentence pairs and coverage-weighted quality. Quality degrades at different rates by system type: hierarchical systems maintain usable-pair rates ranging from 25{\%} to 51{\%} on comparable data while flat systems collapse to 2-7{\%}. Paragraph pre-filtering reduces output volume on comparable data while raising pair quality relative to the unfiltered ablation. Vecalign is statistically indistinguishable from the greedy baseline at all parallelism levels, suggesting that LaBSE embedding discrimination is the binding constraint on flat alignment quality. Failure mode analysis of 550 low-rated pairs identifies topical mismatch as the dominant failure mode, with structural noise concentrated in flat systems."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mash-etal-2026-alignment">
<titleInfo>
<title>Alignment Quality Degradation Across the Parallel–Comparable Spectrum: A Comparative Analysis</title>
</titleInfo>
<name type="personal">
<namePart type="given">Audrey</namePart>
<namePart type="family">Mash</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jonathan</namePart>
<namePart type="given">Ayebakuro</namePart>
<namePart type="family">Orama</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marc</namePart>
<namePart type="given">Juvillà</namePart>
<namePart type="family">Garcia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maite</namePart>
<namePart type="family">Melero</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 26th Annual Conference of the European Association for Machine Translation (Volume 1)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dimitar</namePart>
<namePart type="family">Shterionov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eva</namePart>
<namePart type="family">Vanmassenhove</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mirella</namePart>
<namePart type="family">De Sisto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fred</namePart>
<namePart type="family">Blain</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Javad</namePart>
<namePart type="family">Pourmostafa Roshan Sharami</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lisa</namePart>
<namePart type="family">Lepp</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chiara</namePart>
<namePart type="family">Manna</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Argentina</namePart>
<namePart type="given">Anna</namePart>
<namePart type="family">Rescigno</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alina</namePart>
<namePart type="family">Karakanta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ayla</namePart>
<namePart type="family">Rigouts Terryn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Manuel</namePart>
<namePart type="family">Lardelli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Natalia</namePart>
<namePart type="family">Resende</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elena</namePart>
<namePart type="family">Murgolo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Janiça</namePart>
<namePart type="family">Hackenbuchner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Zaretskaya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Miquel</namePart>
<namePart type="family">Esplà-Gomis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Etchegoyhen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dagmar</namePart>
<namePart type="family">Gromann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rachel</namePart>
<namePart type="family">Bawden</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barry</namePart>
<namePart type="family">Haddow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Szoc</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mikel</namePart>
<namePart type="family">Forcada</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helena</namePart>
<namePart type="family">Moniz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Association for Machine Translation</publisher>
<place>
<placeTerm type="text">Tilburg, The Netherlands</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">9789403901411</identifier>
</relatedItem>
<abstract>Sentence-level alignment systems have been developed and evaluated primarily on parallel data, leaving their behaviour across the broader parallel-comparable spectrum of real web content poorly understood. We present a stratified empirical study of alignment quality for Catalan-English using 300 document pairs across three parallelism bands defined by mean-max LaBSE cosine similarity. We compare four systems: a hierarchical alignment pipeline (DocAlign), an ablation with paragraph pre-filtering disabled (DocAlign-NoFilter), the flat aligner Vecalign, and a flat LaBSE greedy baseline. Evaluation uses human-annotated sentence pairs and coverage-weighted quality. Quality degrades at different rates by system type: hierarchical systems maintain usable-pair rates ranging from 25% to 51% on comparable data while flat systems collapse to 2-7%. Paragraph pre-filtering reduces output volume on comparable data while raising pair quality relative to the unfiltered ablation. Vecalign is statistically indistinguishable from the greedy baseline at all parallelism levels, suggesting that LaBSE embedding discrimination is the binding constraint on flat alignment quality. Failure mode analysis of 550 low-rated pairs identifies topical mismatch as the dominant failure mode, with structural noise concentrated in flat systems.</abstract>
<identifier type="citekey">mash-etal-2026-alignment</identifier>
<location>
<url>https://aclanthology.org/2026.eamt-1.11/</url>
</location>
<part>
<date>2026-06</date>
<extent unit="page">
<start>130</start>
<end>142</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Alignment Quality Degradation Across the Parallel–Comparable Spectrum: A Comparative Analysis
%A Mash, Audrey
%A Orama, Jonathan Ayebakuro
%A Garcia, Marc Juvillà
%A Melero, Maite
%Y Shterionov, Dimitar
%Y Vanmassenhove, Eva
%Y De Sisto, Mirella
%Y Blain, Fred
%Y Pourmostafa Roshan Sharami, Javad
%Y Lepp, Lisa
%Y Manna, Chiara
%Y Rescigno, Argentina Anna
%Y Karakanta, Alina
%Y Rigouts Terryn, Ayla
%Y Lardelli, Manuel
%Y Resende, Natalia
%Y Murgolo, Elena
%Y Hackenbuchner, Janiça
%Y Zaretskaya, Anna
%Y Esplà-Gomis, Miquel
%Y Etchegoyhen, Thierry
%Y Gromann, Dagmar
%Y Bawden, Rachel
%Y Haddow, Barry
%Y Szoc, Sara
%Y Forcada, Mikel
%Y Moniz, Helena
%S Proceedings of the 26th Annual Conference of the European Association for Machine Translation (Volume 1)
%D 2026
%8 June
%I European Association for Machine Translation
%C Tilburg, The Netherlands
%@ 9789403901411
%F mash-etal-2026-alignment
%X Sentence-level alignment systems have been developed and evaluated primarily on parallel data, leaving their behaviour across the broader parallel-comparable spectrum of real web content poorly understood. We present a stratified empirical study of alignment quality for Catalan-English using 300 document pairs across three parallelism bands defined by mean-max LaBSE cosine similarity. We compare four systems: a hierarchical alignment pipeline (DocAlign), an ablation with paragraph pre-filtering disabled (DocAlign-NoFilter), the flat aligner Vecalign, and a flat LaBSE greedy baseline. Evaluation uses human-annotated sentence pairs and coverage-weighted quality. Quality degrades at different rates by system type: hierarchical systems maintain usable-pair rates ranging from 25% to 51% on comparable data while flat systems collapse to 2-7%. Paragraph pre-filtering reduces output volume on comparable data while raising pair quality relative to the unfiltered ablation. Vecalign is statistically indistinguishable from the greedy baseline at all parallelism levels, suggesting that LaBSE embedding discrimination is the binding constraint on flat alignment quality. Failure mode analysis of 550 low-rated pairs identifies topical mismatch as the dominant failure mode, with structural noise concentrated in flat systems.
%U https://aclanthology.org/2026.eamt-1.11/
%P 130-142
Markdown (Informal)
[Alignment Quality Degradation Across the Parallel–Comparable Spectrum: A Comparative Analysis](https://aclanthology.org/2026.eamt-1.11/) (Mash et al., EAMT 2026)
ACL