@inproceedings{pan-hsieh-2026-typological,
title = "Typological Features are Multiple-Choice Questions, not Yes/No Questions: Lessons from Typological Feature-Value Embeddings",
author = "Pan, Tung-Le and
Hsieh, Shu-Kai",
editor = "Adelani, David Ifeoluwa and
Alabi, Jesujoba and
Arnett, Catherine and
Chang, Tyler and
Downey, C.M. and
Goldman, Omer and
Li, Senyu and
Miranda, Lester James Validad and
Qi, Jirui and
Stap, David and
Winata, Genta Indra and
Zhang, Xinyu Crystina",
booktitle = "Proceedings of the 6th Workshop on Multilingual Representation Learning ({MRL} 2026)",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.mrl-1.28/",
pages = "349--365",
ISBN = "979-8-89176-469-9",
abstract = "WALS and Grambank encode typological information in different forms: WALS assigns one value to each multi-valued feature, whereas Grambank mostly records the availability of constructions. Computational pipelines commonly expand both into independent binary columns. We compare that binary encoding with a categorical objective that jointly normalizes the values of each feature. The models otherwise share architecture, data, optimization and capacity. On WALS, the categorical objective recovers more of the structure implicit in feature definitions: distances track ordinal scales, compositional dimensions become consistent directions, and 45{\%} of cross-feature nearest neighbours share a grammatical domain, compared with 20{\%} for the binary model. The advantage persists under reparameterization-invariant diagnostics. External evaluations show the same pattern: categorical embeddings rank independently supported implicational universals more strongly, recover the two clause orders associated with languages lacking a single dominant order even when the corresponding feature is withheld, and correlate more strongly with corpus word-order variability among languages assigned the same WALS label. Held-out-branch prediction differs less between objectives, especially on Grambank. Preserving feature-level competition therefore changes representation geometry even when predictive accuracy changes little."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pan-hsieh-2026-typological">
<titleInfo>
<title>Typological Features are Multiple-Choice Questions, not Yes/No Questions: Lessons from Typological Feature-Value Embeddings</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tung-Le</namePart>
<namePart type="family">Pan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shu-Kai</namePart>
<namePart type="family">Hsieh</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 6th Workshop on Multilingual Representation Learning (MRL 2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="given">Ifeoluwa</namePart>
<namePart type="family">Adelani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jesujoba</namePart>
<namePart type="family">Alabi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Catherine</namePart>
<namePart type="family">Arnett</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tyler</namePart>
<namePart type="family">Chang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">C</namePart>
<namePart type="given">M</namePart>
<namePart type="family">Downey</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Omer</namePart>
<namePart type="family">Goldman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Senyu</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lester</namePart>
<namePart type="given">James</namePart>
<namePart type="given">Validad</namePart>
<namePart type="family">Miranda</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jirui</namePart>
<namePart type="family">Qi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Stap</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Genta</namePart>
<namePart type="given">Indra</namePart>
<namePart type="family">Winata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xinyu</namePart>
<namePart type="given">Crystina</namePart>
<namePart type="family">Zhang</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">979-8-89176-469-9</identifier>
</relatedItem>
<abstract>WALS and Grambank encode typological information in different forms: WALS assigns one value to each multi-valued feature, whereas Grambank mostly records the availability of constructions. Computational pipelines commonly expand both into independent binary columns. We compare that binary encoding with a categorical objective that jointly normalizes the values of each feature. The models otherwise share architecture, data, optimization and capacity. On WALS, the categorical objective recovers more of the structure implicit in feature definitions: distances track ordinal scales, compositional dimensions become consistent directions, and 45% of cross-feature nearest neighbours share a grammatical domain, compared with 20% for the binary model. The advantage persists under reparameterization-invariant diagnostics. External evaluations show the same pattern: categorical embeddings rank independently supported implicational universals more strongly, recover the two clause orders associated with languages lacking a single dominant order even when the corresponding feature is withheld, and correlate more strongly with corpus word-order variability among languages assigned the same WALS label. Held-out-branch prediction differs less between objectives, especially on Grambank. Preserving feature-level competition therefore changes representation geometry even when predictive accuracy changes little.</abstract>
<identifier type="citekey">pan-hsieh-2026-typological</identifier>
<location>
<url>https://aclanthology.org/2026.mrl-1.28/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>349</start>
<end>365</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Typological Features are Multiple-Choice Questions, not Yes/No Questions: Lessons from Typological Feature-Value Embeddings
%A Pan, Tung-Le
%A Hsieh, Shu-Kai
%Y Adelani, David Ifeoluwa
%Y Alabi, Jesujoba
%Y Arnett, Catherine
%Y Chang, Tyler
%Y Downey, C. M.
%Y Goldman, Omer
%Y Li, Senyu
%Y Miranda, Lester James Validad
%Y Qi, Jirui
%Y Stap, David
%Y Winata, Genta Indra
%Y Zhang, Xinyu Crystina
%S Proceedings of the 6th Workshop on Multilingual Representation Learning (MRL 2026)
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-469-9
%F pan-hsieh-2026-typological
%X WALS and Grambank encode typological information in different forms: WALS assigns one value to each multi-valued feature, whereas Grambank mostly records the availability of constructions. Computational pipelines commonly expand both into independent binary columns. We compare that binary encoding with a categorical objective that jointly normalizes the values of each feature. The models otherwise share architecture, data, optimization and capacity. On WALS, the categorical objective recovers more of the structure implicit in feature definitions: distances track ordinal scales, compositional dimensions become consistent directions, and 45% of cross-feature nearest neighbours share a grammatical domain, compared with 20% for the binary model. The advantage persists under reparameterization-invariant diagnostics. External evaluations show the same pattern: categorical embeddings rank independently supported implicational universals more strongly, recover the two clause orders associated with languages lacking a single dominant order even when the corresponding feature is withheld, and correlate more strongly with corpus word-order variability among languages assigned the same WALS label. Held-out-branch prediction differs less between objectives, especially on Grambank. Preserving feature-level competition therefore changes representation geometry even when predictive accuracy changes little.
%U https://aclanthology.org/2026.mrl-1.28/
%P 349-365
Markdown (Informal)
[Typological Features are Multiple-Choice Questions, not Yes/No Questions: Lessons from Typological Feature-Value Embeddings](https://aclanthology.org/2026.mrl-1.28/) (Pan & Hsieh, MRL 2026)
ACL