@inproceedings{shrestha-zhang-2026-coverage,
title = "Coverage Is Not Enough: A Controlled Study of Annotation Selection for Low-Resource Sign Language",
author = "Shrestha, Gyanendra and
Zhang, Liting",
editor = "Singh, Sanjeet and
Joshi, Abhinav and
Dattatreya, Pokala and
Artiaga, Keren and
Pujara, Khushi Jaydeep and
{\v{Z}}elezn{\'y}, Tom{\'a}{\v{s}} and
Gruber, Ivan and
Honz{\'i}k, Jakub and
Kamila, Sabyasachi and
Quiroga, Facundo Manuel and
Hr{\'u}z, Marek and
Hasanuzzaman, Mohammed and
Modi, Ashutosh",
booktitle = "Proceedings of the Second Workshop on Sign Language Processing",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.wslp-1.12/",
pages = "121--131",
ISBN = "979-8-89176-488-0",
abstract = "Expert annotation is a central bottleneck in sign-language corpus construction. A natural assumption is that annotation budgets should prioritize diverse or underrepresented signing patterns. We test this in a controlled retrospective study on PHOENIX14T (German Sign Language) and Isharah (Saudi Sign Language), across gloss recognition, translation, multiple budgets, and three seeds, comparing random sampling against geometric, active-learning, pose-derived articulatory, and privileged selectors. Articulatory coverage is generally weak across all four corpus{--}task settings and rarely outperforms random sampling. A density analysis shows it selects locally atypical clips even after controlling for duration; removing the sparsest 10{--}20{\%} helps at larger budgets but never enough to beat random. A privileged gloss-diversity oracle also performs poorly despite selecting comparatively typical clips, showing that atypicality is not the whole explanation. Facility-location representativeness is the strongest feasible selector in three of four largest-budget settings, with lower WER than random in 16 of 18 seed-matched recognition comparisons, compared with only 2 of 18 for articulatory-only selection. The results suggest pose-derived articulatory coverage and gloss-type coverage, as operationalized here, are unreliable proxies for annotation utility in low-resource sign-language corpus construction. The source code is available at \url{https://github.com/gyan-shrestha/WSLP-2026}."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shrestha-zhang-2026-coverage">
<titleInfo>
<title>Coverage Is Not Enough: A Controlled Study of Annotation Selection for Low-Resource Sign Language</title>
</titleInfo>
<name type="personal">
<namePart type="given">Gyanendra</namePart>
<namePart type="family">Shrestha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Liting</namePart>
<namePart type="family">Zhang</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 Second Workshop on Sign Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sanjeet</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abhinav</namePart>
<namePart type="family">Joshi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pokala</namePart>
<namePart type="family">Dattatreya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Keren</namePart>
<namePart type="family">Artiaga</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khushi</namePart>
<namePart type="given">Jaydeep</namePart>
<namePart type="family">Pujara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tomáš</namePart>
<namePart type="family">Železný</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ivan</namePart>
<namePart type="family">Gruber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jakub</namePart>
<namePart type="family">Honzík</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sabyasachi</namePart>
<namePart type="family">Kamila</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Facundo</namePart>
<namePart type="given">Manuel</namePart>
<namePart type="family">Quiroga</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marek</namePart>
<namePart type="family">Hrúz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammed</namePart>
<namePart type="family">Hasanuzzaman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ashutosh</namePart>
<namePart type="family">Modi</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">979-8-89176-488-0</identifier>
</relatedItem>
<abstract>Expert annotation is a central bottleneck in sign-language corpus construction. A natural assumption is that annotation budgets should prioritize diverse or underrepresented signing patterns. We test this in a controlled retrospective study on PHOENIX14T (German Sign Language) and Isharah (Saudi Sign Language), across gloss recognition, translation, multiple budgets, and three seeds, comparing random sampling against geometric, active-learning, pose-derived articulatory, and privileged selectors. Articulatory coverage is generally weak across all four corpus–task settings and rarely outperforms random sampling. A density analysis shows it selects locally atypical clips even after controlling for duration; removing the sparsest 10–20% helps at larger budgets but never enough to beat random. A privileged gloss-diversity oracle also performs poorly despite selecting comparatively typical clips, showing that atypicality is not the whole explanation. Facility-location representativeness is the strongest feasible selector in three of four largest-budget settings, with lower WER than random in 16 of 18 seed-matched recognition comparisons, compared with only 2 of 18 for articulatory-only selection. The results suggest pose-derived articulatory coverage and gloss-type coverage, as operationalized here, are unreliable proxies for annotation utility in low-resource sign-language corpus construction. The source code is available at https://github.com/gyan-shrestha/WSLP-2026.</abstract>
<identifier type="citekey">shrestha-zhang-2026-coverage</identifier>
<location>
<url>https://aclanthology.org/2026.wslp-1.12/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>121</start>
<end>131</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Coverage Is Not Enough: A Controlled Study of Annotation Selection for Low-Resource Sign Language
%A Shrestha, Gyanendra
%A Zhang, Liting
%Y Singh, Sanjeet
%Y Joshi, Abhinav
%Y Dattatreya, Pokala
%Y Artiaga, Keren
%Y Pujara, Khushi Jaydeep
%Y Železný, Tomáš
%Y Gruber, Ivan
%Y Honzík, Jakub
%Y Kamila, Sabyasachi
%Y Quiroga, Facundo Manuel
%Y Hrúz, Marek
%Y Hasanuzzaman, Mohammed
%Y Modi, Ashutosh
%S Proceedings of the Second Workshop on Sign Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-488-0
%F shrestha-zhang-2026-coverage
%X Expert annotation is a central bottleneck in sign-language corpus construction. A natural assumption is that annotation budgets should prioritize diverse or underrepresented signing patterns. We test this in a controlled retrospective study on PHOENIX14T (German Sign Language) and Isharah (Saudi Sign Language), across gloss recognition, translation, multiple budgets, and three seeds, comparing random sampling against geometric, active-learning, pose-derived articulatory, and privileged selectors. Articulatory coverage is generally weak across all four corpus–task settings and rarely outperforms random sampling. A density analysis shows it selects locally atypical clips even after controlling for duration; removing the sparsest 10–20% helps at larger budgets but never enough to beat random. A privileged gloss-diversity oracle also performs poorly despite selecting comparatively typical clips, showing that atypicality is not the whole explanation. Facility-location representativeness is the strongest feasible selector in three of four largest-budget settings, with lower WER than random in 16 of 18 seed-matched recognition comparisons, compared with only 2 of 18 for articulatory-only selection. The results suggest pose-derived articulatory coverage and gloss-type coverage, as operationalized here, are unreliable proxies for annotation utility in low-resource sign-language corpus construction. The source code is available at https://github.com/gyan-shrestha/WSLP-2026.
%U https://aclanthology.org/2026.wslp-1.12/
%P 121-131
Markdown (Informal)
[Coverage Is Not Enough: A Controlled Study of Annotation Selection for Low-Resource Sign Language](https://aclanthology.org/2026.wslp-1.12/) (Shrestha & Zhang, WSLP 2026)
ACL