@inproceedings{shachar-etal-2025-ner,
title = "{NER} Retriever: Zero-Shot Named Entity Retrieval with Type-Aware Embeddings",
author = "Shachar, Or and
Katz, Uri and
Goldberg, Yoav and
Glickman, Oren",
editor = "Christodoulopoulos, Christos and
Chakraborty, Tanmoy and
Rose, Carolyn and
Peng, Violet",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-emnlp.597/",
pages = "11175--11186",
ISBN = "979-8-89176-335-7",
abstract = "We present NER Retriever, a zero-shot retrieval framework for ad-hoc Named Entity Recognition (NER), where a user-defined type description is used to retrieve documents mentioning entities of that type. Instead of relying on fixed schemas or fine-tuned models, our method builds on pretrained language models (LLMs) to embed both entity mentions and type descriptions into a shared semantic space. We show that internal representations{---}specifically, the value vectors from mid-layer transformer blocks{---}encode fine-grained type information more effectively than commonly used top-layer embeddings. To refine these representations, we train a lightweight contrastive projection network that aligns type-compatible entities while separating unrelated types. The resulting entity embeddings are compact, type-aware, and well-suited for nearest-neighbor search. Evaluated on three benchmarks, NER Retriever significantly outperforms both lexical (BM25) and dense (sentence-level) retrieval baselines, particularly in low-context settings. Our findings provide empirical support for representation selection within LLMs and demonstrate a practical solution for scalable, schema-free entity retrieval."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shachar-etal-2025-ner">
<titleInfo>
<title>NER Retriever: Zero-Shot Named Entity Retrieval with Type-Aware Embeddings</title>
</titleInfo>
<name type="personal">
<namePart type="given">Or</namePart>
<namePart type="family">Shachar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Uri</namePart>
<namePart type="family">Katz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yoav</namePart>
<namePart type="family">Goldberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Oren</namePart>
<namePart type="family">Glickman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2025</title>
</titleInfo>
<name type="personal">
<namePart type="given">Christos</namePart>
<namePart type="family">Christodoulopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carolyn</namePart>
<namePart type="family">Rose</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Violet</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-335-7</identifier>
</relatedItem>
<abstract>We present NER Retriever, a zero-shot retrieval framework for ad-hoc Named Entity Recognition (NER), where a user-defined type description is used to retrieve documents mentioning entities of that type. Instead of relying on fixed schemas or fine-tuned models, our method builds on pretrained language models (LLMs) to embed both entity mentions and type descriptions into a shared semantic space. We show that internal representations—specifically, the value vectors from mid-layer transformer blocks—encode fine-grained type information more effectively than commonly used top-layer embeddings. To refine these representations, we train a lightweight contrastive projection network that aligns type-compatible entities while separating unrelated types. The resulting entity embeddings are compact, type-aware, and well-suited for nearest-neighbor search. Evaluated on three benchmarks, NER Retriever significantly outperforms both lexical (BM25) and dense (sentence-level) retrieval baselines, particularly in low-context settings. Our findings provide empirical support for representation selection within LLMs and demonstrate a practical solution for scalable, schema-free entity retrieval.</abstract>
<identifier type="citekey">shachar-etal-2025-ner</identifier>
<location>
<url>https://aclanthology.org/2025.findings-emnlp.597/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>11175</start>
<end>11186</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T NER Retriever: Zero-Shot Named Entity Retrieval with Type-Aware Embeddings
%A Shachar, Or
%A Katz, Uri
%A Goldberg, Yoav
%A Glickman, Oren
%Y Christodoulopoulos, Christos
%Y Chakraborty, Tanmoy
%Y Rose, Carolyn
%Y Peng, Violet
%S Findings of the Association for Computational Linguistics: EMNLP 2025
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-335-7
%F shachar-etal-2025-ner
%X We present NER Retriever, a zero-shot retrieval framework for ad-hoc Named Entity Recognition (NER), where a user-defined type description is used to retrieve documents mentioning entities of that type. Instead of relying on fixed schemas or fine-tuned models, our method builds on pretrained language models (LLMs) to embed both entity mentions and type descriptions into a shared semantic space. We show that internal representations—specifically, the value vectors from mid-layer transformer blocks—encode fine-grained type information more effectively than commonly used top-layer embeddings. To refine these representations, we train a lightweight contrastive projection network that aligns type-compatible entities while separating unrelated types. The resulting entity embeddings are compact, type-aware, and well-suited for nearest-neighbor search. Evaluated on three benchmarks, NER Retriever significantly outperforms both lexical (BM25) and dense (sentence-level) retrieval baselines, particularly in low-context settings. Our findings provide empirical support for representation selection within LLMs and demonstrate a practical solution for scalable, schema-free entity retrieval.
%U https://aclanthology.org/2025.findings-emnlp.597/
%P 11175-11186
Markdown (Informal)
[NER Retriever: Zero-Shot Named Entity Retrieval with Type-Aware Embeddings](https://aclanthology.org/2025.findings-emnlp.597/) (Shachar et al., Findings 2025)
ACL