Open AccessUsing Named Entities for Recognizing Family Relationships
Author(s) -
Elias Oliveira,
Gihan Dias,
Juan-Fernando Lima,
Juliana Pinheiro Campos Pirovani
Publication year - 2021
Language(s) - English
Resource type - Conference proceedings
DOI - 10.5753/kdmile.2021.17457
Subject(s) - computer science , natural language processing , grammar , artificial intelligence , preprocessor , rule based machine translation , metric (unit) , natural language , relation (database) , entity linking , information extraction , prolog , linguistics , knowledge base , data mining , philosophy , operations management , economics
Named Entity Recognition problem’s objective is to automatically identify and classify entities like persons, places,organizations, and so forth. That is an area in Natural Language Processing and Information Extraction. NamedEntity Recognition is important because it is a fundamental step of preprocessing for several applications like relationextraction. However, it is a hard problem to solve as several categories of named entities are written similarly andthey appear in similar contexts. To accomplish it, we can use some hybrid approaches. Nevertheless, in this presentstudy, we use linguistic flavor by applying Local Grammar and Cascade of Transducers. Local Grammars are used torepresent the rules of a particular linguistic structure. They are often built manually to describe the entities we aimto recognize. In our study, we adapted a Local Grammar to improve the Recognition of Named Entities. The resultsshow an improvement of up to 7% on the F-measure metric in relation to the previous Local Grammar. Also, we builtanother Local Grammar to recognize family relationships from the improved Local Grammar. We present a practicalapplication for the extracted relationships using Prolog.