@inproceedings{kim-etal-2026-user,
title = "When Does User-Scoped Glossary Injection Recover {ASR}-Corrupted Domain Terms in Meeting Summarization? Separating Term Recovery from Summary Utility",
author = "Kim, Gihwan and
Lim, Hyoung Jun and
Chung, Yoonseo and
Park, Heeyong and
Jeong, ChangHyeon and
Ma, Seunghee and
Park, Joohye and
Kim, Junghwan",
editor = "Atanasova, Pepa and
Haffari, Gholamreza and
Wang, Minghan",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-industry.180/",
pages = "3056--3068",
ISBN = "979-8-89176-460-6",
abstract = "Prompt-level glossary injection can recover ASR-corrupted domain terms, but its effectiveness depends sharply on glossary scope. In enterprise meeting summarization, a black-box STT system passes only a 1-best transcript to the summarizer; its errors on loanwords, acronyms, and domain terms can replace the canonical forms needed downstream. Motivated by the keyword-input UX of a deployed Korean meeting summarization service, we evaluate training-free prompt-level injection of an annotation-derived meeting-scoped glossary proxy without transcript rewriting. On 30 public Korean meetings processed offline by operational STT, 27{\%} of annotated terms are corrupted under normalized matching, and a no-glossary summarizer recovers only 1.3{\%} of these corrupted terms. Meeting-scoped injection raises term recovery to 53.8{\%}, with 89.2{\%} of output keywords grounded in the transcript. The effect collapses under broader scopes: on the same 45 terms, meeting-level recovery is 66.7{\%} versus 6.7{\%} for a 2,669-term full-dictionary proxy. Coverage-controlled size sweeps show this collapse on Qwen3-8B, and three EXAONE-3.5 points reproduce it, indicating prompt-level over-biasing. A four-annotator human evaluation does not establish improved summary utility; we therefore treat domain-term recovery as an operational dimension, not a summary-preference proxy. We contribute a public-data evaluation protocol and deployment analysis of domain-term recovery under black-box STT constraints."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kim-etal-2026-user">
<titleInfo>
<title>When Does User-Scoped Glossary Injection Recover ASR-Corrupted Domain Terms in Meeting Summarization? Separating Term Recovery from Summary Utility</title>
</titleInfo>
<name type="personal">
<namePart type="given">Gihwan</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hyoung</namePart>
<namePart type="given">Jun</namePart>
<namePart type="family">Lim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yoonseo</namePart>
<namePart type="family">Chung</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heeyong</namePart>
<namePart type="family">Park</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">ChangHyeon</namePart>
<namePart type="family">Jeong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seunghee</namePart>
<namePart type="family">Ma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joohye</namePart>
<namePart type="family">Park</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junghwan</namePart>
<namePart type="family">Kim</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 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track</title>
</titleInfo>
<name type="personal">
<namePart type="given">Pepa</namePart>
<namePart type="family">Atanasova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gholamreza</namePart>
<namePart type="family">Haffari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Minghan</namePart>
<namePart type="family">Wang</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">979-8-89176-460-6</identifier>
</relatedItem>
<abstract>Prompt-level glossary injection can recover ASR-corrupted domain terms, but its effectiveness depends sharply on glossary scope. In enterprise meeting summarization, a black-box STT system passes only a 1-best transcript to the summarizer; its errors on loanwords, acronyms, and domain terms can replace the canonical forms needed downstream. Motivated by the keyword-input UX of a deployed Korean meeting summarization service, we evaluate training-free prompt-level injection of an annotation-derived meeting-scoped glossary proxy without transcript rewriting. On 30 public Korean meetings processed offline by operational STT, 27% of annotated terms are corrupted under normalized matching, and a no-glossary summarizer recovers only 1.3% of these corrupted terms. Meeting-scoped injection raises term recovery to 53.8%, with 89.2% of output keywords grounded in the transcript. The effect collapses under broader scopes: on the same 45 terms, meeting-level recovery is 66.7% versus 6.7% for a 2,669-term full-dictionary proxy. Coverage-controlled size sweeps show this collapse on Qwen3-8B, and three EXAONE-3.5 points reproduce it, indicating prompt-level over-biasing. A four-annotator human evaluation does not establish improved summary utility; we therefore treat domain-term recovery as an operational dimension, not a summary-preference proxy. We contribute a public-data evaluation protocol and deployment analysis of domain-term recovery under black-box STT constraints.</abstract>
<identifier type="citekey">kim-etal-2026-user</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-industry.180/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>3056</start>
<end>3068</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T When Does User-Scoped Glossary Injection Recover ASR-Corrupted Domain Terms in Meeting Summarization? Separating Term Recovery from Summary Utility
%A Kim, Gihwan
%A Lim, Hyoung Jun
%A Chung, Yoonseo
%A Park, Heeyong
%A Jeong, ChangHyeon
%A Ma, Seunghee
%A Park, Joohye
%A Kim, Junghwan
%Y Atanasova, Pepa
%Y Haffari, Gholamreza
%Y Wang, Minghan
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-460-6
%F kim-etal-2026-user
%X Prompt-level glossary injection can recover ASR-corrupted domain terms, but its effectiveness depends sharply on glossary scope. In enterprise meeting summarization, a black-box STT system passes only a 1-best transcript to the summarizer; its errors on loanwords, acronyms, and domain terms can replace the canonical forms needed downstream. Motivated by the keyword-input UX of a deployed Korean meeting summarization service, we evaluate training-free prompt-level injection of an annotation-derived meeting-scoped glossary proxy without transcript rewriting. On 30 public Korean meetings processed offline by operational STT, 27% of annotated terms are corrupted under normalized matching, and a no-glossary summarizer recovers only 1.3% of these corrupted terms. Meeting-scoped injection raises term recovery to 53.8%, with 89.2% of output keywords grounded in the transcript. The effect collapses under broader scopes: on the same 45 terms, meeting-level recovery is 66.7% versus 6.7% for a 2,669-term full-dictionary proxy. Coverage-controlled size sweeps show this collapse on Qwen3-8B, and three EXAONE-3.5 points reproduce it, indicating prompt-level over-biasing. A four-annotator human evaluation does not establish improved summary utility; we therefore treat domain-term recovery as an operational dimension, not a summary-preference proxy. We contribute a public-data evaluation protocol and deployment analysis of domain-term recovery under black-box STT constraints.
%U https://aclanthology.org/2026.emnlp-industry.180/
%P 3056-3068
Markdown (Informal)
[When Does User-Scoped Glossary Injection Recover ASR-Corrupted Domain Terms in Meeting Summarization? Separating Term Recovery from Summary Utility](https://aclanthology.org/2026.emnlp-industry.180/) (Kim et al., EMNLP 2026)
ACL
- Gihwan Kim, Hyoung Jun Lim, Yoonseo Chung, Heeyong Park, ChangHyeon Jeong, Seunghee Ma, Joohye Park, and Junghwan Kim. 2026. When Does User-Scoped Glossary Injection Recover ASR-Corrupted Domain Terms in Meeting Summarization? Separating Term Recovery from Summary Utility. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track, pages 3056–3068, Budapest, Hungary. Association for Computational Linguistics.