Facebook Integrated Chatbot for Bulgarian Language Aiding Learning Content Delivery

The paper presents a chatbot oriented linguistic approach and a software prototype which addresses the need of delivering learning content based on queries in Bulgarian language. Two distinct database query generation approaches are presented, discussed and implemented. Pros and cons for each of them are discussed.

SPARQL Query Generator (SQG)

This paper describes a program—SPARQL Query Generator (SQG)—which takes as input an OWL ontology, a set of object descriptions in terms of this ontology and an OWL class as the context, and generates relatively large numbers of queries about various types of descriptions of objects expressed in RDF/OWL. The intent is to use SQG in evaluating data representation and retrieval systems from the perspective of OWL semantics coverage. While there are many benchmarks for assessing the efficiency of data retrieval systems, none of the existing solutions for SPARQL query generation focus on the coverage of the OWL semantics. Some are not scalable since manual work is needed for the generation process; some do not consider (or totally ignore) the OWL semantics in the ontology/instance data or rely on large numbers of real queries/datasets that are not readily available in our domain of interest. Our experimental results show that SQG performs reasonably well with generating large numbers of queries and guarantees a good coverage of OWL axioms included in the generated queries.

Natural Language to SQL query Generation

Today, everyone has a personal device to access the web. Every user tries to access the knowledge that they require through internet. Most of the knowledge is within the sort of a database. A user with limited knowledge of database will have difficulty in accessing the data in the database. Hence, there’s a requirement for a system that permits the users to access the knowledge within the database. The proposed method is to develop a system where the input be a natural language and receive an SQL query which is used to access the database and retrieve the information with ease. Tokenization, parts-of-speech tagging, lemmatization, parsing and mapping are the steps involved in the process. The project proposed would give a view of using of Natural Language Processing (NLP) and mapping the query in accordance with regular expression in English language to SQL.