Improving Candidate Retrieval with Entity Profile Generation for Wikidata Entity Linking
There is little work on entity linking (EL) over Wikidata, even though it is the most extensive crowdsourced knowledge base. The scale of Wikidata can open up many new real-world applications, but its massive number of entities also makes EL challenging. To effectively narrow down the search space, we propose a novel candidate retrieval paradigm based on entity profiling. Wikidata entities and their textual fields are first indexed into a text search engine (e.g., Elasticsearch). During inference, given a mention and its context, we use a sequence-to-sequence (seq2seq) model to generate the profile of the target entity, which consists of its title and description. We use the profile to query the indexed search engine to retrieve candidate entities. Our approach complements the traditional approach of using a Wikipedia anchor-text dictionary, enabling us to further design a highly effective hybrid method for candidate retrieval. Combined with a simple cross-attention reranker, our complete EL framework achieves state-of-the-art results on three Wikidata-based datasets and strong performance on TACKBP-2010.
Code (0)
등록된 구현이 없습니다.
Tasks
Entity LinkingProfile GenerationRetrievalSimilar Papers 제목 키워드 기반
Improving Candidate Retrieval with Entity Profile Generation for Wikidata Entity Linking
Entity linking (EL) is the task of linking entity mentions in a document to referent entities in a knowledge base (KB). Many previous studies focus on Wikipedia-derived KBs. There is little work on EL over Wikidata, even…
Entity LinkingProfile GenerationRetrievalFalcon 2.0: An Entity and Relation Linking Tool over Wikidata
The Natural Language Processing (NLP) community has significantly contributed to the solutions for entity and relation recognition from the text, and possibly linking them to proper matches in Knowledge Graphs (KGs). Con…
Knowledge Base Question AnsweringKnowledge GraphsLanguage ModellingRelation+1Wikontic: Constructing Wikidata-Aligned, Ontology-Aware Knowledge Graphs with Large Language Models
Knowledge graphs (KGs) provide structured, verifiable grounding for large language models (LLMs), but current LLM-based systems commonly use KGs as auxiliary structures for text retrieval, leaving their intrinsic quality…
Knowledge GraphsText RetrievalOverview of the Ugglan Entity Discovery and Linking System
Ugglan is a system designed to discover named entities and link them to unique identifiers in a knowledge base. It is based on a combination of a name and nominal dictionary derived from Wikipedia and Wikidata, a named e…
named-entity-recognitionNamed Entity RecognitionNamed Entity Recognition (NER)NERSAGA: Schema-Aware Grounding for Agentic Text-to-SPARQL Generation
Complex knowledge base question answering (KBQA) is commonly approached through either information retrieval over a question-specific subgraph or semantic parsing into an executable logical form. We study the latter para…
Knowledge Base Question AnsweringInformation RetrievalSemantic Parsing