@inproceedings{ayasi-2026-ht,
title = "{HT} {WMT} 2026 {C}reole{MT} System Description: Learning Hierarchies for Low-Resource Creole Language Identification",
author = "Ayasi, Ananya",
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.185/",
pages = "2405--2413",
ISBN = "979-8-89176-474-3",
abstract = "This work is a submission to the Creole MT Creole Language Identification Shared Task conducted as a part of the Eleventh Conference on Machine Translation (WMT `26) colocated with EMNLP 2026, investigating whether hierarchical classification can improve language identification for closely related French-lexifier Creoles. We compare expert-designed linguistic hierarchies with data-driven hierarchies learned from model confusions and representation similarity, together with both hard and soft routing strategies. All models are built on a shared character-level TF{--}IDF representation with linear classifiers and are evaluated against a strong flat LinearSVC baseline and the multilingual GlotLID system. The best-performing approach is a data-driven combined hierarchy with soft routing, achieving a Macro-F1 of 87.54 while maintaining one of the lowest Macro False Positive Rates (0.00485). Analysis shows that training data availability remains the strongest predictor of language-level performance, with recall significantly correlated with training set size. Manual inspection further reveals that most remaining errors arise from named entities, lexical borrowing, noisy text, and confusions between closely related Creole varieties. Overall, our results demonstrate that learned hierarchical organization provides a practical and effective alternative to expert-designed taxonomies for low-resource language identification while offering improved balance between classification performance and false-positive control."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ayasi-2026-ht">
<titleInfo>
<title>HT WMT 2026 CreoleMT System Description: Learning Hierarchies for Low-Resource Creole Language Identification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ananya</namePart>
<namePart type="family">Ayasi</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>This work is a submission to the Creole MT Creole Language Identification Shared Task conducted as a part of the Eleventh Conference on Machine Translation (WMT ‘26) colocated with EMNLP 2026, investigating whether hierarchical classification can improve language identification for closely related French-lexifier Creoles. We compare expert-designed linguistic hierarchies with data-driven hierarchies learned from model confusions and representation similarity, together with both hard and soft routing strategies. All models are built on a shared character-level TF–IDF representation with linear classifiers and are evaluated against a strong flat LinearSVC baseline and the multilingual GlotLID system. The best-performing approach is a data-driven combined hierarchy with soft routing, achieving a Macro-F1 of 87.54 while maintaining one of the lowest Macro False Positive Rates (0.00485). Analysis shows that training data availability remains the strongest predictor of language-level performance, with recall significantly correlated with training set size. Manual inspection further reveals that most remaining errors arise from named entities, lexical borrowing, noisy text, and confusions between closely related Creole varieties. Overall, our results demonstrate that learned hierarchical organization provides a practical and effective alternative to expert-designed taxonomies for low-resource language identification while offering improved balance between classification performance and false-positive control.</abstract>
<identifier type="citekey">ayasi-2026-ht</identifier>
<location>
<url>https://aclanthology.org/2026.wmt-main.185/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>2405</start>
<end>2413</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T HT WMT 2026 CreoleMT System Description: Learning Hierarchies for Low-Resource Creole Language Identification
%A Ayasi, Ananya
%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 ayasi-2026-ht
%X This work is a submission to the Creole MT Creole Language Identification Shared Task conducted as a part of the Eleventh Conference on Machine Translation (WMT ‘26) colocated with EMNLP 2026, investigating whether hierarchical classification can improve language identification for closely related French-lexifier Creoles. We compare expert-designed linguistic hierarchies with data-driven hierarchies learned from model confusions and representation similarity, together with both hard and soft routing strategies. All models are built on a shared character-level TF–IDF representation with linear classifiers and are evaluated against a strong flat LinearSVC baseline and the multilingual GlotLID system. The best-performing approach is a data-driven combined hierarchy with soft routing, achieving a Macro-F1 of 87.54 while maintaining one of the lowest Macro False Positive Rates (0.00485). Analysis shows that training data availability remains the strongest predictor of language-level performance, with recall significantly correlated with training set size. Manual inspection further reveals that most remaining errors arise from named entities, lexical borrowing, noisy text, and confusions between closely related Creole varieties. Overall, our results demonstrate that learned hierarchical organization provides a practical and effective alternative to expert-designed taxonomies for low-resource language identification while offering improved balance between classification performance and false-positive control.
%U https://aclanthology.org/2026.wmt-main.185/
%P 2405-2413
Markdown (Informal)
[HT WMT 2026 CreoleMT System Description: Learning Hierarchies for Low-Resource Creole Language Identification](https://aclanthology.org/2026.wmt-main.185/) (Ayasi, WMT 2026)
ACL