NER-FL: A Novel Named Entity Recognizer of Farsi Languageusing the Web-Based Natural Language Processors and Semantic Annotations

Abstract

Named Entity Recognition is a main task in the NLP area that has yielded multiple web-based natural language processors gaining popularity in the Semantic Web community for extracting knowledge from web data. These processors are generally located as pipelines, using dedicated APIs and various taxonomy for extracting, classifying and disambiguating named entities. In this paper, we address the problem of NER on Farsi language by proposing NER-FL, a novel semantic framework which unifies three popular named entity extractors available on the web, and the NER-FL ontology which provides a rich set of axioms aligning the taxonomies of these web natural language processors automatically on the LOD-cloud. KEYWORDSWeb-based natural language processor, named entity, semantic web, ontology, Farsi language

A Novel Connectivity-based Reinforcement Learning Algorithm for Ranking Linked Data on the Social Semantic Web

“…Hence, it can be concluded that LD_Rank has high performance in LOD. As future works, we plan to explore positive outcomes of appropriate RDF ranking in different applications such as Question Answering [17] and NE disambiguation [18] in the context of property tagging.…”