concept

entity linking

Also known as: EL, entity linking model

Facts (36)

Sources

Construction of Knowledge Graphs: State and Challenges - arXiv arxiv.org arXiv 18 facts

claimEntity Linking systems face specific challenges including coreference resolution, where entities are referred to indirectly (e.g., via pronouns), and the handling of emerging entities that are recognized but not yet present in the target Knowledge Graph.

claimPre-trained word embeddings assist in the Entity Linking disambiguation process by encoding semantic similarity within a latent space.

claimInvestigating the application of entity resolution techniques designed for dirty data sources to entity linking tasks represents a potential research opportunity.

claimThe entity linking component of knowledge extraction can render an additional entity resolution step unnecessary in knowledge graph construction.

claimEntity Linking algorithms can improve the linking of entities by leveraging previously disambiguated mentions located within the same paragraph.

claimEntity linking and entity resolution are sometimes collectively referred to as 'entity canonicalization' because both processes aim to connect the same entities within and across data sources.

claimEntity Linking algorithms utilize various features for disambiguation, including the confidence score of the Named Entity Recognition (NER) tool, the similarity between the mention and the candidate entity, and the overlap across mentions.

claimThe XI Pipeline performs entity linking by combining probabilistic models and microtask crowdsourcing, which outperforms models that do not use a human-in-the-loop paradigm.

claimData integration and canonicalization in knowledge graphs involve entity linking, entity resolution, entity fusion, and the matching and merging of ontology concepts and properties.

referenceHolistic entity linking is an approach that utilizes background knowledge and inter-dependencies between different information sources to improve entity linking performance, a topic surveyed by Oliveira et al. in 2021.

claimEntity linking in knowledge graphs is performed using various methods, including dictionary-based approaches relying on gathered synonyms in AI-KG, human interaction in XI, or entity resolution in HKGB.

claimIn the context of Entity Linking, 'commonness' is defined as the probability that an entity mention links to the specific Wikipedia article of a candidate entity, while 'relatedness' measures the number of Wikipedia articles that link to both candidate entities.

referenceZenCrowd is a system that leverages probabilistic reasoning and crowdsourcing techniques to perform large-scale entity linking, as presented by Demartini, Difallah, and Cudré-Mauroux at the 21st World Wide Web Conference in 2012.

claimEntity Linking algorithms can use TF-IDF scores of rare keywords found in the context of a mention to identify connections to candidate entities.

claimEntity Linking (EL) or Named Entity Disambiguation (NED) is the process of linking recognized named entities in text to a knowledge base or Knowledge Graph (KG) by selecting the correct entity from a set of candidates.

procedureText-based knowledge representation involves three main steps: named-entity recognition, entity linking, and relation extraction.

claimKnowledge Extraction is the process of deriving structured information and knowledge from unstructured or semi-structured data using techniques such as named entity recognition, entity linking, relation extraction, and the canonicalization of entity and relation identifiers.

procedureUsing a dictionary (also called a lexicon or gazetteer) is a reliable and simple method to detect entity mentions in text, as it maps labels of desired entities to identifiers in a knowledge graph, effectively performing named-entity recognition and entity linking in a single step.

Practices, opportunities and challenges in the fusion of knowledge ... frontiersin.org Frontiers 9 facts

referenceReFinED, proposed by Ayoola et al. (2022), uses fine-grained entity types and entity descriptions to construct an efficient end-to-end entity linking model that can be generalized to other large-scale knowledge bases.

referenceChatEL, proposed by Ding Y. et al. (2024), is a three-step framework that leverages large language models for entity linking by generating candidate entities, enhancing contextual information, and incorporating a multiple-choice format.

referenceAyoola et al. (2022) developed REFINED, an efficient zero-shot-capable approach to end-to-end entity linking, as described in arXiv preprint arXiv:2207.04108.

claimEntity Linking (EL) is the process of matching text mentions to specific entities in a knowledge base to enhance text understanding and information retrieval.

claimThe fusion of large language models (LLMs) and knowledge graphs (KGs) encounters representational conflicts between the implicit statistical patterns of LLMs and the explicit symbolic structures of KGs, which disrupts entity linking consistency.

referenceXin et al. (2024) developed 'LLMAEL', a method using large language models as context augmenters for entity linking.

claimLarge Language Models (LLMs) assist in Knowledge Graph construction by acting as prompts and generators for entity, relation, and event extraction, as well as performing entity linking and coreference resolution.

referenceThe paper 'Chatel: entity linking with chatbots' (arXiv:2402.14858) explores the application of chatbots for entity linking tasks.

claimKnowledge graph-enhanced large language models often incur high computational overhead due to the necessity of graph traversal, entity linking, and dynamic retrieval during inference, which introduces latency that hinders deployment in real-time applications like dialogue systems, autonomous agents, and online recommendation.

Neuro-Symbolic AI: Explainability, Challenges, and Future Trends arxiv.org arXiv Nov 7, 2024 2 facts

claimJiang et al. (2021) proposed LNN-EL (Logical Neural Network-Entity Linking), an entity link prediction method that converts logical rules into the network structure of a Logical Neural Network to solve entity linking in short texts.

referenceThe category 'Explicit Intermediate Representations or Explicit Decision Making' in neuro-symbolic AI contains three studies: entity linking (Jiang et al., 2021), NVM-based robotic manipulation (Katz et al., 2021), and Question and Answering (Kapanipathi et al., 2020).

KG-RAG: Bridging the Gap Between Knowledge and Creativity - arXiv arxiv.org arXiv May 20, 2024 2 facts

claimFuture research could improve the quality and reliability of the knowledge graphs used by CoE by integrating advanced methods such as entity resolution (Binette et al., 2022) and entity linking (Shen et al., 2021).

Large Language Models Meet Knowledge Graphs for Question ... arxiv.org arXiv Sep 22, 2025 2 facts

claimQuestion answering (QA) is a fundamental component in artificial intelligence, natural language processing, information retrieval, and data management, with applications including text generation, chatbots, dialog generation, web search, entity linking, natural language query, and fact-checking.

referenceKnowledge integration and fusion enhance language models by aligning knowledge graphs and text via local subgraph extraction and entity linking, then feeding the aligned data into a cross-model encoder to bidirectionally fuse text and knowledge graphs for joint training.

How NebulaGraph Fusion GraphRAG Bridges the Gap Between ... nebula-graph.io NebulaGraph Jan 27, 2026 1 fact

claimBuilding a knowledge graph traditionally requires NLP expertise in named entity recognition, relationship extraction, and entity linking, alongside significant volumes of labeled data and model fine-tuning.

A survey on augmenting knowledge graphs (KGs) with large ... link.springer.com Springer Nov 4, 2024 1 fact

procedureSemantic parsing, entity linking, and relation extraction are techniques used to implement semantic layers by extracting and inferring critical concepts and relationships from data to feed into LLMs during processing.

LLM-empowered knowledge graph construction: A survey - arXiv arxiv.org arXiv Oct 23, 2025 1 fact

referenceYifan Ding, Amrit Poudel, Qingkai Zeng, Tim Weninger, Balaji Veeramani, and Sanmitra Bhattacharya authored 'EntGPT: Entity Linking with Generative Large Language Models', published as an arXiv preprint in May 2025.