Semantic search using Natural Language Processing

Aiza Kupiyalova, Ryskhan Satybaldiyeva, Serik Aiaskarov

2020

Closed access Metadata (CSL-JSON)
DOI 10.1109/cbi49978.2020.10065
Data confidence 70 medium
How this score is calculated

It is built from checkable properties of the record itself: whether the article has a DOI, how many independent sources confirmed its data, whether the required fields are filled in, and how recent the latest confirmation is. Disagreement between sources and a missing identifier lower it. A value of 80 or above means the record was published without further checking; 60 to 79 means it is published at reduced confidence, with a manual check advisable. A record verified by an editor by hand is never pushed below 90 by a recalculation. This scores our data about the article, not the article itself.

Abstract

Natural Language Processing (NLP) is a computerized way of analyzing texts. NLP involves the acquisition of knowledge on how a person understands and uses language. This is for the development of appropriate tools and techniques that allow computer systems to understand and manipulate natural languages to perform various desirable tasks. This article reviews the literature in the NLP. It also provides information about NLP history. Additionally it provides architectural design for semantic search tool using NLP, and discussed architectural modules, domain and constraints. This work proposes future possibilities for research and its application.