Abstract
The main restriction of the Semantic Web is the difficulty of the SPARQL language, which is necessary for extracting information from the Knowledge Representation also known as ontology. Making the Semantic Web accessible for people who do not know SPARQL is essential for the use of friendlier interfaces, and a good alternative is Natural Language. This paper shows the implementation of a friendly prototype interface activated by voice to query and retrieving information from websites built with Semantic Web tools. In that way, the end users avoid the complicated SPARQL language. To achieve this, the interface recognizes a speech query and converts it into text, it processes the text through a Java program and identifies keywords, generates a SPARQL query, extracts the information from the website and reads it in a voice for the user. In our work, Google Cloud Speech API makes Speech-to-Text conversions and Text-to Speech conversions are made with SVOX Pico. As a result, we have measured three variables: the success rate in queries, the response time of query and a usability survey. The values of the variables allow the evaluation of our prototype. Finally, the interface proposed provides us with a new approach in the problem, using the Cloud like a Service, reducing barriers of access to the Semantic Web for people without technical knowledge of Semantic Web technologies.
Highlights
The rise of the World Wide Web (WWW) in the last few years has increased the difficulty of finding relevant information about specific study subjects
The proposed architecture is a Speech Interface that can make queries and obtain responses by voice, linked to a platform designed with the semantic web tools, OWL, SPARQL, ontologies, etc
We supply the experimental achievement of the performance of Speech Interface in terms of three variables such as: the success rate in queries, the response time of query and the usability of the system
Summary
The rise of the World Wide Web (WWW) in the last few years has increased the difficulty of finding relevant information about specific study subjects (mainly because of the ambiguity problems with the terms used in the searching tools). There are several works about the generation of Natural Language Interfaces (NLI) to query ontologies that have received a wide attentiveness and they allow users to depict arbitrarily convoluted information. Zheng presents a system that uses the contents of a website where the base-knowledge is stored This designed system successfully uses natural language processing and information recovery techniques to achieve large response rates [6]. With this designed interface, accessing barriers will be reduced for people without technical knowledge of the Semantic Web. in our work to achieve voice queries, it will be necessary to use cloud computing because it supplies services over the Internet.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
