NER Retriever: Zero-Shot Named Entity Retrieval with Type-Aware Embeddings

• URL: http://arxiv.org/abs/2509.04011v1
• Date: Thu, 04 Sep 2025 08:42:23 GMT
• Title: NER Retriever: Zero-Shot Named Entity Retrieval with Type-Aware Embeddings
• Authors: Or Shachar, Uri Katz, Yoav Goldberg, Oren Glickman,
• Abstract summary: We present NER Retriever, a zero-shot retrieval framework for ad-hoc Named Entity Retrieval.<n>Instead of relying on fixed schemas or fine-tuned models, our method builds on internal representations of large language models.<n>We show that internal representations, specifically the value from mid-layer transformer blocks, encode fine-grained type information more effectively than commonly used top-layer embeddings.
• Score: 22.99473179665451
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We present NER Retriever, a zero-shot retrieval framework for ad-hoc Named Entity Retrieval, a variant of Named Entity Recognition (NER), where the types of interest are not provided in advance, and 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 internal representations of large language models (LLMs) to embed both entity mentions and user-provided open-ended 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 and dense sentence-level retrieval baselines. Our findings provide empirical support for representation selection within LLMs and demonstrate a practical solution for scalable, schema-free entity retrieval. The NER Retriever Codebase is publicly available at https://github.com/ShacharOr100/ner_retriever

Related papers

• Language-driven Fine-grained Retrieval [56.619978313798875]
  We introduce LaFG, a Language-driven framework for Fine-Grained Retrieval.<n>It converts class names into attribute-level supervision using large language models and vision-language models.<n>A global prompt template selects category-relevant attributes, which are aggregated into category-specific linguistic prototypes.
  arXiv  Detail & Related papers  (2025-12-06T02:56:55Z)
• DyVo: Dynamic Vocabularies for Learned Sparse Retrieval with Entities [29.716152560414738]
  We enhance the Learned Sparse Retrieval (LSR) model with Wikipedia concepts and entities. In experiments across three entity-rich document ranking datasets, the resulting DyVo model substantially outperforms state-of-the-art baselines.
  arXiv  Detail & Related papers  (2024-10-10T08:41:34Z)
• Entity Disambiguation via Fusion Entity Decoding [68.77265315142296]
  We propose an encoder-decoder model to disambiguate entities with more detailed entity descriptions. We observe +1.5% improvements in end-to-end entity linking in the GERBIL benchmark compared with EntQA.
  arXiv  Detail & Related papers  (2024-04-02T04:27:54Z)
• Large-Scale Label Interpretation Learning for Few-Shot Named Entity Recognition [5.262708162539423]
  Few-shot named entity recognition (NER) detects named entities within text using only a few examples. One promising line of research is to leverage natural language descriptions of each entity type. In this paper, we explore the impact of a strong semantic prior to interpret verbalizations of new entity types.
  arXiv  Detail & Related papers  (2024-03-21T08:22:44Z)
• NERetrieve: Dataset for Next Generation Named Entity Recognition and Retrieval [49.827932299460514]
  We argue that capabilities provided by large language models are not the end of NER research, but rather an exciting beginning. We present three variants of the NER task, together with a dataset to support them. We provide a large, silver-annotated corpus of 4 million paragraphs covering 500 entity types.
  arXiv  Detail & Related papers  (2023-10-22T12:23:00Z)
• PromptNER: A Prompting Method for Few-shot Named Entity Recognition via k Nearest Neighbor Search [56.81939214465558]
  We propose PromptNER: a novel prompting method for few-shot NER via k nearest neighbor search. We use prompts that contains entity category information to construct label prototypes, which enables our model to fine-tune with only the support set. Our approach achieves excellent transfer learning ability, and extensive experiments on the Few-NERD and CrossNER datasets demonstrate that our model achieves superior performance over state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-05-20T15:47:59Z)
• Automatic Creation of Named Entity Recognition Datasets by Querying Phrase Representations [20.00016240535205]
  Most weakly supervised named entity recognition models rely on domain-specific dictionaries provided by experts. We present a novel framework, HighGEN, that generates NER datasets with high-coverage pseudo-dictionaries. We demonstrate that HighGEN outperforms the previous best model by an average F1 score of 4.7 across five NER benchmark datasets.
  arXiv  Detail & Related papers  (2022-10-14T07:36:44Z)
• UnifieR: A Unified Retriever for Large-Scale Retrieval [84.61239936314597]
  Large-scale retrieval is to recall relevant documents from a huge collection given a query. Recent retrieval methods based on pre-trained language models (PLM) can be coarsely categorized into either dense-vector or lexicon-based paradigms. We propose a new learning framework, UnifieR which unifies dense-vector and lexicon-based retrieval in one model with a dual-representing capability.
  arXiv  Detail & Related papers  (2022-05-23T11:01:59Z)
• MuVER: Improving First-Stage Entity Retrieval with Multi-View Entity Representations [28.28940043641958]
  We propose a novel approach for entity retrieval that constructs multi-view representations for entity descriptions and approximates the optimal view for mentions via a searching method. Our method achieves the state-of-the-art performance on ZESHEL and improves the quality of candidates on three standard Entity Linking datasets.
  arXiv  Detail & Related papers  (2021-09-13T05:51:45Z)
• Interpretable Entity Representations through Large-Scale Typing [61.4277527871572]
  We present an approach to creating entity representations that are human readable and achieve high performance out of the box. Our representations are vectors whose values correspond to posterior probabilities over fine-grained entity types. We show that it is possible to reduce the size of our type set in a learning-based way for particular domains.
  arXiv  Detail & Related papers  (2020-04-30T23:58:03Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.