Asking the Right Questions: Ontology-Grounded Interpretable Embeddings for Biomedical Text

arXiv:2603.01690 · cs.CL, cs.AI · Submitted 2026-03-02 · Read on arXiv

cs.CL, cs.AI

Submitted: 2026-03-02

Updated: 2026-09-07

Comments: EMNLP 2026 (Findings)

Code: https://github.com/L1nzh/QIME

License: http://creativecommons.org/licenses/by-nc-nd/4.0/

The gist: While dense biomedical embeddings achieve strong performance, their opaque dimensions limit transparency in biomedical NLP.

Terminology

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.

Sources

Related papers