@inproceedings{shipton-etal-2026-simple,
title = "Simple Additions, Substantial Gains: Expanding Scripts, Languages, and Lineage Coverage in {URIEL}+",
author = {Shipton, Mason and
Ng, York Hay and
Khan, Aditya and
Hoang, Phuong H. and
Lu, Xiang and
Do{\u{g}}ru{\"o}z, A. Seza and
Lee, Annie En-Shiun},
editor = "Piperidis, Stelios and
Bel, N{\'u}ria and
van den Heuvel, Henk and
Ide, Nancy and
Krek, Simon and
Toral, Antonio",
booktitle = "Proceedings of the Fifteenth Language Resources and Evaluation Conference",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "ELRA Language Resource Association",
url = "https://aclanthology.org/2026.lrec-1.863/",
doi = "10.63317/5e6qapi74t97",
pages = "11045--11059",
abstract = "The URIEL+ linguistic knowledge base supports multilingual research by encoding languages through geographic, genetic, and typological vectors. However, data sparsity (e.g. missing feature types, incomplete language entries, and limited genealogical coverage) remains prevalent. This limits the usefulness of URIEL+ in cross-lingual transfer, particularly for supporting low-resource languages. To address this sparsity, we extend URIEL+ by introducing script vectors to represent writing system properties for 7,488 languages, integrating Glottolog to add 18,710 additional languages, and expanding lineage imputation for 26,449 languages by propagating typological and script features across genealogies. These improvements reduce feature sparsity by 14{\%} for script vectors, increase language coverage by up to 19,015 languages (1,007{\%}), and boost imputation quality metrics by up to 35{\%}. Our benchmark on cross-lingual transfer tasks (oriented around low-resource languages) shows occasionally divergent performance compared to URIEL+, with performance gains up to 6{\%} in certain setups."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shipton-etal-2026-simple">
<titleInfo>
<title>Simple Additions, Substantial Gains: Expanding Scripts, Languages, and Lineage Coverage in URIEL+</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mason</namePart>
<namePart type="family">Shipton</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">York</namePart>
<namePart type="given">Hay</namePart>
<namePart type="family">Ng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aditya</namePart>
<namePart type="family">Khan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Phuong</namePart>
<namePart type="given">H</namePart>
<namePart type="family">Hoang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiang</namePart>
<namePart type="family">Lu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">A</namePart>
<namePart type="given">Seza</namePart>
<namePart type="family">Doğruöz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Annie</namePart>
<namePart type="given">En-Shiun</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Núria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henk</namePart>
<namePart type="family">van den Heuvel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nancy</namePart>
<namePart type="family">Ide</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Krek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Toral</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resource Association</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The URIEL+ linguistic knowledge base supports multilingual research by encoding languages through geographic, genetic, and typological vectors. However, data sparsity (e.g. missing feature types, incomplete language entries, and limited genealogical coverage) remains prevalent. This limits the usefulness of URIEL+ in cross-lingual transfer, particularly for supporting low-resource languages. To address this sparsity, we extend URIEL+ by introducing script vectors to represent writing system properties for 7,488 languages, integrating Glottolog to add 18,710 additional languages, and expanding lineage imputation for 26,449 languages by propagating typological and script features across genealogies. These improvements reduce feature sparsity by 14% for script vectors, increase language coverage by up to 19,015 languages (1,007%), and boost imputation quality metrics by up to 35%. Our benchmark on cross-lingual transfer tasks (oriented around low-resource languages) shows occasionally divergent performance compared to URIEL+, with performance gains up to 6% in certain setups.</abstract>
<identifier type="citekey">shipton-etal-2026-simple</identifier>
<identifier type="doi">10.63317/5e6qapi74t97</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.863/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>11045</start>
<end>11059</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Simple Additions, Substantial Gains: Expanding Scripts, Languages, and Lineage Coverage in URIEL+
%A Shipton, Mason
%A Ng, York Hay
%A Khan, Aditya
%A Hoang, Phuong H.
%A Lu, Xiang
%A Doğruöz, A. Seza
%A Lee, Annie En-Shiun
%Y Piperidis, Stelios
%Y Bel, Núria
%Y van den Heuvel, Henk
%Y Ide, Nancy
%Y Krek, Simon
%Y Toral, Antonio
%S Proceedings of the Fifteenth Language Resources and Evaluation Conference
%D 2026
%8 May
%I ELRA Language Resource Association
%C Palma de Mallorca, Spain
%F shipton-etal-2026-simple
%X The URIEL+ linguistic knowledge base supports multilingual research by encoding languages through geographic, genetic, and typological vectors. However, data sparsity (e.g. missing feature types, incomplete language entries, and limited genealogical coverage) remains prevalent. This limits the usefulness of URIEL+ in cross-lingual transfer, particularly for supporting low-resource languages. To address this sparsity, we extend URIEL+ by introducing script vectors to represent writing system properties for 7,488 languages, integrating Glottolog to add 18,710 additional languages, and expanding lineage imputation for 26,449 languages by propagating typological and script features across genealogies. These improvements reduce feature sparsity by 14% for script vectors, increase language coverage by up to 19,015 languages (1,007%), and boost imputation quality metrics by up to 35%. Our benchmark on cross-lingual transfer tasks (oriented around low-resource languages) shows occasionally divergent performance compared to URIEL+, with performance gains up to 6% in certain setups.
%R 10.63317/5e6qapi74t97
%U https://aclanthology.org/2026.lrec-1.863/
%U https://doi.org/10.63317/5e6qapi74t97
%P 11045-11059
Markdown (Informal)
[Simple Additions, Substantial Gains: Expanding Scripts, Languages, and Lineage Coverage in URIEL+](https://aclanthology.org/2026.lrec-1.863/) (Shipton et al., LREC 2026)
ACL
- Mason Shipton, York Hay Ng, Aditya Khan, Phuong H. Hoang, Xiang Lu, A. Seza Doğruöz, and Annie En-Shiun Lee. 2026. Simple Additions, Substantial Gains: Expanding Scripts, Languages, and Lineage Coverage in URIEL+. In Proceedings of the Fifteenth Language Resources and Evaluation Conference, pages 11045–11059, Palma de Mallorca, Spain. ELRA Language Resource Association.