@inproceedings{tang-etal-2026-asking,
title = "Asking the Right Questions: Ontology-Grounded Interpretable Embeddings for Biomedical Text",
author = "Tang, Yixuan and
Lin, Zhenghong and
Sun, Yandong and
Hsu, Wynne and
Lee, Mong-Li and
Tung, Anthony Kum Hoe",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-emnlp.1149/",
pages = "24332--24344",
ISBN = "979-8-89176-462-0",
abstract = "While dense biomedical embeddings achieve strong performance, their opaque dimensions limit transparency in biomedical NLP. Recent question-based interpretable embeddings represent text through binary answers to natural-language questions, but existing approaches rely primarily on corpus-driven signals, often capturing topical or stylistic differences rather than fine-grained biomedical distinctions. We propose QIME, an ontology-grounded framework for interpretable biomedical text embeddings in which each dimension corresponds to an explicit biomedical-domain yes/no question. QIME leverages a biomedical ontology to guide contrastive question generation from semantic clusters, producing atomic, domain-grounded questions. It constructs embeddings via similarity-based semantic activation with MMR-based diversity-aware dimension selection, yielding sparse representations efficiently. Experiments on biomedical clustering, STS and retrieval benchmarks show that QIME consistently outperforms prior interpretable embedding methods and substantially narrows the gap to strong black-box biomedical encoders. It also imposes substantially lower cognitive burden than existing methods, providing concise and domain-specific interpretations. The code is available at https://github.com/L1nzh/QIME."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tang-etal-2026-asking">
<titleInfo>
<title>Asking the Right Questions: Ontology-Grounded Interpretable Embeddings for Biomedical Text</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yixuan</namePart>
<namePart type="family">Tang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhenghong</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yandong</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wynne</namePart>
<namePart type="family">Hsu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mong-Li</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anthony</namePart>
<namePart type="given">Kum</namePart>
<namePart type="given">Hoe</namePart>
<namePart type="family">Tung</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>Findings of the Association for Computational Linguistics: EMNLP 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</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">979-8-89176-462-0</identifier>
</relatedItem>
<abstract>While dense biomedical embeddings achieve strong performance, their opaque dimensions limit transparency in biomedical NLP. Recent question-based interpretable embeddings represent text through binary answers to natural-language questions, but existing approaches rely primarily on corpus-driven signals, often capturing topical or stylistic differences rather than fine-grained biomedical distinctions. We propose QIME, an ontology-grounded framework for interpretable biomedical text embeddings in which each dimension corresponds to an explicit biomedical-domain yes/no question. QIME leverages a biomedical ontology to guide contrastive question generation from semantic clusters, producing atomic, domain-grounded questions. It constructs embeddings via similarity-based semantic activation with MMR-based diversity-aware dimension selection, yielding sparse representations efficiently. Experiments on biomedical clustering, STS and retrieval benchmarks show that QIME consistently outperforms prior interpretable embedding methods and substantially narrows the gap to strong black-box biomedical encoders. It also imposes substantially lower cognitive burden than existing methods, providing concise and domain-specific interpretations. The code is available at https://github.com/L1nzh/QIME.</abstract>
<identifier type="citekey">tang-etal-2026-asking</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.1149/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>24332</start>
<end>24344</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Asking the Right Questions: Ontology-Grounded Interpretable Embeddings for Biomedical Text
%A Tang, Yixuan
%A Lin, Zhenghong
%A Sun, Yandong
%A Hsu, Wynne
%A Lee, Mong-Li
%A Tung, Anthony Kum Hoe
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F tang-etal-2026-asking
%X While dense biomedical embeddings achieve strong performance, their opaque dimensions limit transparency in biomedical NLP. Recent question-based interpretable embeddings represent text through binary answers to natural-language questions, but existing approaches rely primarily on corpus-driven signals, often capturing topical or stylistic differences rather than fine-grained biomedical distinctions. We propose QIME, an ontology-grounded framework for interpretable biomedical text embeddings in which each dimension corresponds to an explicit biomedical-domain yes/no question. QIME leverages a biomedical ontology to guide contrastive question generation from semantic clusters, producing atomic, domain-grounded questions. It constructs embeddings via similarity-based semantic activation with MMR-based diversity-aware dimension selection, yielding sparse representations efficiently. Experiments on biomedical clustering, STS and retrieval benchmarks show that QIME consistently outperforms prior interpretable embedding methods and substantially narrows the gap to strong black-box biomedical encoders. It also imposes substantially lower cognitive burden than existing methods, providing concise and domain-specific interpretations. The code is available at https://github.com/L1nzh/QIME.
%U https://aclanthology.org/2026.findings-emnlp.1149/
%P 24332-24344
Markdown (Informal)
[Asking the Right Questions: Ontology-Grounded Interpretable Embeddings for Biomedical Text](https://aclanthology.org/2026.findings-emnlp.1149/) (Tang et al., Findings 2026)
ACL