@inproceedings{lynch-etal-2026-structured,
title = "Structured Entity Extraction from {H}awaiian Television Chyrons Using Vision-Language Models",
author = "Lynch, Kelley and
King, Owen and
Rim, Kyeongmin and
Keen, Gabrielle and
Chen, Yangyang and
Pustejovsky, James",
editor = "Ojha, Atul Kr. and
Sakti, Sakriani and
Soria, Claudia and
Melero, Maite and
McCrae, John P. and
Lignos, Constantine and
Liu, Chao-Hong and
Claramunt, German Rigau and
Rehm, Georg",
booktitle = "Proceedings of the {SIGUL} 2026 Joint Workshop with {ELE}, {EURALI}, and {DCLRL}: Towards Inclusivity and Equality: Language Resources and Technologies for Under-Resourced and Endangered Languages",
month = may,
year = "2026",
address = "Palma, Mallorca, Spain",
publisher = "ELRA Language Resources Association (ELRA)",
url = "https://aclanthology.org/2026.sigul-1.17/",
doi = "10.63317/4vjma77xc4kh",
pages = "160--168",
abstract = "Hawaiian (ʻ{\={O}}lelo Hawaiʻi) is an endangered Polynesian language whose broadcast archives represent a critical yet underutilized resource for language documentation. We present the first evaluation of vision-language models (VLMs) for structured entity extraction from television chyrons, investigating the performance gap between Hawaiian-language content and mainland U.S. comparisons. Using our new HiChy dataset of 3,925 manually annotated images, we demonstrate that Hawaiian content remains significantly more challenging for current VLMs: for the best-performing model (Qwen2.5-VL-7B), character error rates roughly double from 0.064 on mainland data to 0.130 on Hawaiian content. We extend the task to key information extraction (KIE), finding that while models can perform structured parsing, they struggle specifically with names of Hawaiian linguistic origin, a difficulty that persists even when controlling for geographic source. Across five evaluated models spanning local quantized inference and commercial APIs, we find that OCR accuracy and structured extraction capability do not necessarily correlate: the best OCR model (Gemini 3 Flash) underperforms locally-deployed alternatives on KIE, while even a 2.2B-parameter model (SmolVLM2) achieves functional extraction. Our results provide a baseline for AI-assisted archival processing of underrepresented language media and highlight the need for models that better account for the orthographic and cultural specificities of Hawaiian."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lynch-etal-2026-structured">
<titleInfo>
<title>Structured Entity Extraction from Hawaiian Television Chyrons Using Vision-Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kelley</namePart>
<namePart type="family">Lynch</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Owen</namePart>
<namePart type="family">King</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kyeongmin</namePart>
<namePart type="family">Rim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gabrielle</namePart>
<namePart type="family">Keen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yangyang</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">James</namePart>
<namePart type="family">Pustejovsky</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 SIGUL 2026 Joint Workshop with ELE, EURALI, and DCLRL: Towards Inclusivity and Equality: Language Resources and Technologies for Under-Resourced and Endangered Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Atul</namePart>
<namePart type="given">Kr.</namePart>
<namePart type="family">Ojha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Claudia</namePart>
<namePart type="family">Soria</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maite</namePart>
<namePart type="family">Melero</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">John</namePart>
<namePart type="given">P</namePart>
<namePart type="family">McCrae</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Constantine</namePart>
<namePart type="family">Lignos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chao-Hong</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">German</namePart>
<namePart type="given">Rigau</namePart>
<namePart type="family">Claramunt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Georg</namePart>
<namePart type="family">Rehm</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Palma, Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Hawaiian (ʻŌlelo Hawaiʻi) is an endangered Polynesian language whose broadcast archives represent a critical yet underutilized resource for language documentation. We present the first evaluation of vision-language models (VLMs) for structured entity extraction from television chyrons, investigating the performance gap between Hawaiian-language content and mainland U.S. comparisons. Using our new HiChy dataset of 3,925 manually annotated images, we demonstrate that Hawaiian content remains significantly more challenging for current VLMs: for the best-performing model (Qwen2.5-VL-7B), character error rates roughly double from 0.064 on mainland data to 0.130 on Hawaiian content. We extend the task to key information extraction (KIE), finding that while models can perform structured parsing, they struggle specifically with names of Hawaiian linguistic origin, a difficulty that persists even when controlling for geographic source. Across five evaluated models spanning local quantized inference and commercial APIs, we find that OCR accuracy and structured extraction capability do not necessarily correlate: the best OCR model (Gemini 3 Flash) underperforms locally-deployed alternatives on KIE, while even a 2.2B-parameter model (SmolVLM2) achieves functional extraction. Our results provide a baseline for AI-assisted archival processing of underrepresented language media and highlight the need for models that better account for the orthographic and cultural specificities of Hawaiian.</abstract>
<identifier type="citekey">lynch-etal-2026-structured</identifier>
<identifier type="doi">10.63317/4vjma77xc4kh</identifier>
<location>
<url>https://aclanthology.org/2026.sigul-1.17/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>160</start>
<end>168</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Structured Entity Extraction from Hawaiian Television Chyrons Using Vision-Language Models
%A Lynch, Kelley
%A King, Owen
%A Rim, Kyeongmin
%A Keen, Gabrielle
%A Chen, Yangyang
%A Pustejovsky, James
%Y Ojha, Atul Kr.
%Y Sakti, Sakriani
%Y Soria, Claudia
%Y Melero, Maite
%Y McCrae, John P.
%Y Lignos, Constantine
%Y Liu, Chao-Hong
%Y Claramunt, German Rigau
%Y Rehm, Georg
%S Proceedings of the SIGUL 2026 Joint Workshop with ELE, EURALI, and DCLRL: Towards Inclusivity and Equality: Language Resources and Technologies for Under-Resourced and Endangered Languages
%D 2026
%8 May
%I ELRA Language Resources Association (ELRA)
%C Palma, Mallorca, Spain
%F lynch-etal-2026-structured
%X Hawaiian (ʻŌlelo Hawaiʻi) is an endangered Polynesian language whose broadcast archives represent a critical yet underutilized resource for language documentation. We present the first evaluation of vision-language models (VLMs) for structured entity extraction from television chyrons, investigating the performance gap between Hawaiian-language content and mainland U.S. comparisons. Using our new HiChy dataset of 3,925 manually annotated images, we demonstrate that Hawaiian content remains significantly more challenging for current VLMs: for the best-performing model (Qwen2.5-VL-7B), character error rates roughly double from 0.064 on mainland data to 0.130 on Hawaiian content. We extend the task to key information extraction (KIE), finding that while models can perform structured parsing, they struggle specifically with names of Hawaiian linguistic origin, a difficulty that persists even when controlling for geographic source. Across five evaluated models spanning local quantized inference and commercial APIs, we find that OCR accuracy and structured extraction capability do not necessarily correlate: the best OCR model (Gemini 3 Flash) underperforms locally-deployed alternatives on KIE, while even a 2.2B-parameter model (SmolVLM2) achieves functional extraction. Our results provide a baseline for AI-assisted archival processing of underrepresented language media and highlight the need for models that better account for the orthographic and cultural specificities of Hawaiian.
%R 10.63317/4vjma77xc4kh
%U https://aclanthology.org/2026.sigul-1.17/
%U https://doi.org/10.63317/4vjma77xc4kh
%P 160-168
Markdown (Informal)
[Structured Entity Extraction from Hawaiian Television Chyrons Using Vision-Language Models](https://aclanthology.org/2026.sigul-1.17/) (Lynch et al., SIGUL-EURALI-DCLRL 2026)
ACL
- Kelley Lynch, Owen King, Kyeongmin Rim, Gabrielle Keen, Yangyang Chen, and James Pustejovsky. 2026. Structured Entity Extraction from Hawaiian Television Chyrons Using Vision-Language Models. In Proceedings of the SIGUL 2026 Joint Workshop with ELE, EURALI, and DCLRL: Towards Inclusivity and Equality: Language Resources and Technologies for Under-Resourced and Endangered Languages, pages 160–168, Palma, Mallorca, Spain. ELRA Language Resources Association (ELRA).