Survey on English Entity Linking on Wikidata

Abstract

Wikidata is a frequently updated, community-driven, and multilingual knowledge graph. Hence, Wikidata is an attractive basis for Entity Linking, which is evident by the recent increase in published papers. This survey focuses on four subjects:(1) Which Wikidata Entity Linking datasets exist, how widely used are they and how are they constructed? (2) Do the characteristics of Wikidata matter for the design of Entity Linking datasets and if so, how? (3) How do current Entity Linking approaches exploit the specific characteristics of Wikidata? (4) Which Wikidata characteristics are unexploited by existing Entity Linking approaches? This survey reveals that current Wikidata-specific Entity Linking datasets do not differ in their annotation scheme from schemes for other knowledge graphs like DBpedia. Thus, the potential for multilingual and time-dependent datasets, naturally suited for Wikidata, is not lifted. Furthermore, we show that most Entity Linking approaches use Wikidata in the same way as any other knowledge graph missing the chance to leverage Wikidata-specific characteristics to increase quality. Almost all approaches employ specific properties like labels and sometimes descriptions but ignore characteristics such as the hyperrelational structure. Hence, there is still room for improvement, for example, by including hyper-relational graph embeddings or type information. Many approaches also include information from Wikipedia, which is easily combinable with Wikidata and provides valuable textual information, which Wikidata lacks.

BLINK with Elasticsearch for Efficient Entity Linking in Business Conversations

“…Prior work on entity linking mostly focused on linking named entities to unstructured knowledge bases like Wikipedia, whereas the amount of work that used a structured knowledge base like Wikidata is very limited (Shen et al, 2014;Sakor et al, 2020). Though other knowledge bases like DBpedia (Auer et al, 2007) or YAGO (Fabian et al, 2007) have also been studied, the utilization of Wikidata as the knowledge base to extract relevant information has gained lots of attention recently (Lin et al, 2021;Möller et al, 2021). Detecting mentions (i.e., entities) in the given text (Huang et al, 2015;Akbik et al, 2018) is an important step for entity linking.…”

Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Industry Track

“…Prior work on entity linking mostly focused on linking named entities to unstructured knowledge bases like Wikipedia, whereas the amount of work that used a structured knowledge base like Wikidata is very limited (Shen et al, 2014;. Though other knowledge bases like DBpedia (Auer et al, 2007) or YAGO (Fabian et al, 2007) have also been studied, the utilization of Wikidata as the knowledge base to extract relevant information has gained lots of attention recently Möller et al, 2021). Detecting mentions (i.e., entities) in the given text (Huang et al, 2015;Akbik et al, 2018) is an important step for entity linking.…”

Robust Chinese Short Text Entity Disambiguation Method Based on Feature Fusion and Contrastive Learning

“…To address the aforementioned challenges, we propose COLBERT, which stands for combining Contrastive Learning with LDA and BERT for short-text entity disambiguation. COLBERT leverages the prevalent entity-linking-based disambiguation approach, where mentions of ambiguous entities are mapped to referent entities in an external knowledge base by matching algorithms [12]. The proposed method involves transforming the entity disambiguation task into a classification task by combining short texts with descriptions of referent entities from the knowledge base.…”