@inproceedings{goldner-gramazio-2026-chainalign,
title = "{C}hain{A}lign: Cross-Lingual Sentence Alignment via Sparse Co-linear Chaining",
author = "Goldner, Owen and
Gramazio, Connor",
editor = "Haddow, Barry and
Kocmi, Tom and
Koehn, Philipp and
Monz, Christof",
booktitle = "Proceedings of the Eleventh Conference on Machine Translation",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.wmt-main.11/",
pages = "183--198",
ISBN = "979-8-89176-474-3",
abstract = "Cross-lingual sentence alignment establishes correspondence between a document and its translation, where correspondence is not always complete, one-to-one, or monotonic. Current embedding-based aligners score sentence pairs with a multilingual encoder, then trace a single monotonic path across the full alignment grid. This forced path cascades errors through non-parallel or reordered content. We present ChainAlign, which instead adapts *seed-chain-extend* from computational genomics: it seeds multi-resolution candidate anchors from multilingual embeddings, selects the maximum-weight non-crossing subset by co-linear chaining in *O(N log N)* via a Fenwick tree, and fills the residual gaps with local dynamic time warping. Because the chain imposes no coverage requirement, non-parallel content becomes unaligned gaps rather than cascading errors, and multi-chain extraction handles reordering that a monotonic path cannot represent. On three benchmarks across four language pairs, ChainAlign achieves the highest strict and lax F1, ahead of Bertalign, SentAlign, and Vecalign. Evaluation shows the sparse formulation outperforms exhaustive dynamic programming using the same edge weight function."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="goldner-gramazio-2026-chainalign">
<titleInfo>
<title>ChainAlign: Cross-Lingual Sentence Alignment via Sparse Co-linear Chaining</title>
</titleInfo>
<name type="personal">
<namePart type="given">Owen</namePart>
<namePart type="family">Goldner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Connor</namePart>
<namePart type="family">Gramazio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Eleventh Conference on Machine Translation</title>
</titleInfo>
<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">Tom</namePart>
<namePart type="family">Kocmi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philipp</namePart>
<namePart type="family">Koehn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christof</namePart>
<namePart type="family">Monz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-474-3</identifier>
</relatedItem>
<abstract>Cross-lingual sentence alignment establishes correspondence between a document and its translation, where correspondence is not always complete, one-to-one, or monotonic. Current embedding-based aligners score sentence pairs with a multilingual encoder, then trace a single monotonic path across the full alignment grid. This forced path cascades errors through non-parallel or reordered content. We present ChainAlign, which instead adapts *seed-chain-extend* from computational genomics: it seeds multi-resolution candidate anchors from multilingual embeddings, selects the maximum-weight non-crossing subset by co-linear chaining in *O(N log N)* via a Fenwick tree, and fills the residual gaps with local dynamic time warping. Because the chain imposes no coverage requirement, non-parallel content becomes unaligned gaps rather than cascading errors, and multi-chain extraction handles reordering that a monotonic path cannot represent. On three benchmarks across four language pairs, ChainAlign achieves the highest strict and lax F1, ahead of Bertalign, SentAlign, and Vecalign. Evaluation shows the sparse formulation outperforms exhaustive dynamic programming using the same edge weight function.</abstract>
<identifier type="citekey">goldner-gramazio-2026-chainalign</identifier>
<location>
<url>https://aclanthology.org/2026.wmt-main.11/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>183</start>
<end>198</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ChainAlign: Cross-Lingual Sentence Alignment via Sparse Co-linear Chaining
%A Goldner, Owen
%A Gramazio, Connor
%Y Haddow, Barry
%Y Kocmi, Tom
%Y Koehn, Philipp
%Y Monz, Christof
%S Proceedings of the Eleventh Conference on Machine Translation
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-474-3
%F goldner-gramazio-2026-chainalign
%X Cross-lingual sentence alignment establishes correspondence between a document and its translation, where correspondence is not always complete, one-to-one, or monotonic. Current embedding-based aligners score sentence pairs with a multilingual encoder, then trace a single monotonic path across the full alignment grid. This forced path cascades errors through non-parallel or reordered content. We present ChainAlign, which instead adapts *seed-chain-extend* from computational genomics: it seeds multi-resolution candidate anchors from multilingual embeddings, selects the maximum-weight non-crossing subset by co-linear chaining in *O(N log N)* via a Fenwick tree, and fills the residual gaps with local dynamic time warping. Because the chain imposes no coverage requirement, non-parallel content becomes unaligned gaps rather than cascading errors, and multi-chain extraction handles reordering that a monotonic path cannot represent. On three benchmarks across four language pairs, ChainAlign achieves the highest strict and lax F1, ahead of Bertalign, SentAlign, and Vecalign. Evaluation shows the sparse formulation outperforms exhaustive dynamic programming using the same edge weight function.
%U https://aclanthology.org/2026.wmt-main.11/
%P 183-198
Markdown (Informal)
[ChainAlign: Cross-Lingual Sentence Alignment via Sparse Co-linear Chaining](https://aclanthology.org/2026.wmt-main.11/) (Goldner & Gramazio, WMT 2026)
ACL