Enhancing the Open-Domain Classification of Named Entity Using Linked Open Data

Abstract

Abstract. Many applications make use of named entity classification. Machine learning is the preferred technique adopted for many named entity classification methods where the choice of features is critical to final performance. Existing approaches explore only the features derived from the characteristic of the named entity itself or its linguistic context. With the development of the Semantic Web, a large number of data sources are published and connected across the Web as Linked Open Data (LOD). LOD provides rich a priori knowledge about entity type information, knowledge that can be a valuable asset when used in connection with named entity classification. In this paper, we explore the use of LOD to enhance named entity classification. Our method extracts information from LOD and builds a type knowledge base which is used to score a (named entity string, type) pair. This score is then injected as one or more features into the existing classifier in order to improve its performance. We conducted a thorough experimental study and report the results, which confirm the effectiveness of our proposed method.

Named entity recognition and disambiguation using linked data and graph-based centrality scoring

“…Ni et al propose a method that extracts information from LOD about entities and builds a type-oriented knowledge base [6]. Named entities are scored based on their types and then this score is used in an existing classifier.…”

“…Each surface form has a candidate list of entities and if any surface form contains multiple entities then that surface form should be disambiguated. 6 http://dbpedia.org/Lexicalizations 7 http://dbpedia.org/ontology/wikiPageDisambiguates 8 http://dbpedia.org/ontology/wikiPageRedirects…”

Entity discovery and annotation in tables

“…Ni et al [16] harness the richness of the Linked Open Data (LOD) to create a type knowledge base that they use to compute the probability that an entity has a given type. However, while the LOD is a rich collection of RDF triples that express facts on millions of entities, many types of entities are still under-represented, as witnessed by the "Linked Data Shopping List", documented on the website linkeddata.org 5 .…”

Prospective Client Driven Technology Recommendation

“…The knowledge bases or external dictionaries also help named entity classification. Knowledge bases were used to generate the entity seed list for semi-supervised entity classification [14] (based on Wikipedia and IMDB), or server as the priori entity knowledge to enhance the posteriori score of an entity belonging to an entity type assigned by a classifier [9] (based on Linked Open Data on the Web). The external search engine is also a useful tool utilized by [7] to screen context features of the labelled named entity mentions in documents.…”