Entity Linking with a Knowledge Base: Issues, Techniques, and Solutions

By Wei Shen, Jianyong Wang, Jiawei Han. 2015

827 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Information Systems, Management Science and Operations Research

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Information Systems

In Management Science and Operations Research

Citations in the corpus

Mention and Entity Description Co-Attention for Entity Disambiguation (2018, background): “Among all these aspects, it has been widely accepted that semantic similarity between the context of an entity mention and its target entity candidates is the key to resolve the ambiguity (Bunescu and Pasca 2006; Cucerzan 2007; Ji and Grishman 2011; Shen, Wang, and Han 2015).”
OAG: Toward Linking Large-scale Heterogeneous Entity Graphs (2019, background): “The problem of entity linking is related to entity matching [20, 25, 36], entity resolution [2, 3], web appearance disambiguation [1, 11], name identification [16], object distinction [37], and name disambiguation [8, 30, 40], and has been extensively studied for decades by different communities.”
Entity Disambiguation with Web Links (2015, methodology): “The availability of Wikipedia, in particular, has driven work on EL, knowledge base population (KBP), and semantic search.”
Relation Extraction Using Distant Supervision (2018, background): “We refer a reader to the survey on entity linking systems [59].”
Sound and Music Recommendation with Knowledge Graphs (2016, methodology): “Entity Linking tools usually execute a pipe of three main procedures [Shen et al. 2015]: candidate entity generation , candidate entity ranking , and unlinkable mention prediction .”
Alana v2: Entertaining and Informative Open-domain Social Dialogue using Ontologies and Entity Linking (2018, background): “This task is known as Entity Linking and it is defined by Shen et al. (2015) as follows: “Given a knowledge base containing a set of entities E and a text collection in which a set of named entity mentions M are identified in advance, the goal of entity linking is to map each textual entity mention…”
Self-Alignment Pretraining for Biomedical Entity Representations (2020, background): “Beyond the biomedical domain, entity linking has been intensively investigated on the less challenging general domain (Shen et al., 2015; Kolitsas et al., 2018).”
Document Retrieval Model Through Semantic Linking (2017, background): “Cornolti et al. [6] provide a benchmarking framework for comparing annotation systems and analyse some of the popular systems such as TagMe [9], Wikipedia-miner [23], and DBpedia Spotlight [20].”
Deep Learning for Entity Matching: A Design Space Exploration (2018, background): “Entity Linking: Entity linking aims at linking entity mentions in an input document (usually a small piece of text) to a canonical entity in a knowledge base [66].”
Knowledge Graphs 2021: A Data Odyssey (2021, background): “The KB does not resolve this name ambiguity by itself as different entities share alias names, but the KB provides the foundation for downstream disambiguation: entity linking for mentions in texts or tables [32].”
Evaluating the Impact of Knowledge Graph Context on Entity Disambiguation Models (2020, background): “iterature for Entity Linking (EL) ranging from graph traversal [28], rule-based [23], to Neural Network-based approaches [7, 19]. For detailed information on entity linking we refer to the surveys in [1, 25]. Herein, we restrict ourselves to very closely related recent literature. Advances in Neural”
Design Challenges for Entity Linking (2015, background): “Most related work has been discussed in the earlier sections; see Shen et al. (2014) for an EL survey.”
Learning Dynamic Context Augmentation for Global Entity Linking (2019, methodology): “Approximation methods, such as loopy belief propagation (Ganea and Hofmann, 2017) or iterative substitutions (Shen et al., 2015), are still computationally expensive due to the huge hypothesis space, and thus can hardly be scaled to handle large corpus.”