ACCESSING DATABASE USING NLP

International Journal of Scientific Research in Computer Science and Engineering, 2018

Now a day"s a computer plays a vital role in almost all the sectors/application. The available information is stored and retrieved in/from the database. Database Management system (such as SQL, Oracle) allows to handle the database by creation of the database, querying the database, updating database, and administration of databases. So there is need of skilled person (database experts) in order to deal with database management system, but this is not always true. The common people with lack of expertise are there to handle the database, who doesn"t know about the syntax/format of queries to be fire on the database. Also they are more comfortable in their native languages like "Marathi", "Hindi", "Arabic". It is essential to have the database interface in native language (e.g Marathi) so that the non-expert person can also interact with database for storing and extracting the data. In this paper we are proposing the Marathi language interface using Natural Language Processing (NLP) to handle the database. This interface can handle the queries in native language which may be syntactically and semantically incorrect and convert it into correct form.(e.g SQL query). Rest of the paper is organized as follows, Section I contains the introduction of natural language processing , Section II contain the related work of natural language interface to the database system, Section III contain the problem definition and proposed system, Section IV contain the architecture and algorithm of proposed system, section V explain the working of proposed system with example, Section VI give conclusion with future direction.

It was highly desirable for a machine to interact more friendly with the users so that the field of Natural Language Processing (NLP) emerged and Natural Language Interface to Databases (NLIDBs) systems are built and design. A major problem faced by the users of the data bases is that the databases generally make use of special purpose languages familiar only to the trained users like Structured Query Language (SQL). Natural Language Interface to Databases provides the interface in which queries are written in the form Natural Language. These queries are passed through the machine, machine translates these queries. There are different levels of it, after passing these levels machine produce relevant results. This paper will provides comprehensive understanding about Natural Language Processing and Natural Language Interface to Databases.

2015

Database management systems have been used for storing and retrieving the data. Databases are very hard to use since their interfaces is rigid in cooperating with users. Almost all e-governance applications are using databases. They are providing services like weather forecasting, agriculture, banking, railway etc. people who are snug with Hindi language needs these applications to accept Hindi sentence as a query, process it and after execution provide the result to the user in Hindi language itself. Natural language processing (NLP) plays an important role while working on Hindi language to make it more efficient for the common people. Here we have developed the rule based system which will satisfy the user need and it will accept Hindi language as query and gives out put in Hindi language only.

IJCSMC, Vol. 3, Issue. 4, April 2014, pg.1179 – 1189 , 2014

We require information in our daily life. One of the major sources of information is database. Almost all applications have need to retrieve information from database which require knowledge of database languages like SQL. To write SQL query one need to have not only knowledge query language but also the physical structure of Database. Therefore everybody is not able to write SQL queries. To override the complexity many researchers have turned out to use Natural Language (NL) i.e Hindi, English, French, Tamil etc. instead of SQL. The idea of using NL has prompted the development of new type of processing method called Natural Language Interface to Database systems (NLIDB). This paper discusses the architecture of mapping the Hindi language query entered by the user into SQL query.

Enormous amount of data are being processed and exchanged in our daily life, and database, which is used to organize data has been an active research topic for a long time. Database plays a major role in many computer systems and there is always a demand from technical and nontechnical people to ease the process of accessing data on database. Using Natural Language to directly interact with a database is a nice and user friendly solution. In order to achieve this type of communication between the computer (In particular, database) and human we have to make the computer understand what the human asks, and then, be able to respond with the right answer that was expected to be extracted from the database. In this paper we present an intelligent system for converting Natural Language queries into equivalent database Structured Query Language (SQL). Our system also allows processing complex Natural Language queries. We call this Intelligent Agent based Natural Language Interface to Database (INLIDB). The query results from the INLIDB is presented in an attractive succinctly viewable format. We have obtained encouraging results from INLIDB.

Database management systems have been widely used for storing and retrieving data. However, databases are difficult to use and there interface is complex and the same is difficult to access. To make it easy for a user to retrieve data, an interface is developed in which a database can be accessed by a user through querying in Hindi language and to get the result in same language. In order to develop an improved Hindi language graphical user interface to database management system. The proposed system can handle single and multiple columns retrieval queries, selection of whole table, conditional queries (between, in), join queries and queries that include nested, functions and logical operators. Since a user should not be able to update or delete data from database so the user is suggest on selection queries.

In the present computing world, computer based information technologies have been extensively used to help many organizations, private companies, academic and education institutions to manage their processes and information systems. A general information management system that is capable of managing several kinds of data, stored in the database is known as Database Management System (DBMS). Database Management System is a collection of interrelated data and set of programs to access those data. In this paper, we have designed and developed Amharic Language Interface for database, so that user can easily communicate with database without the knowledge of database language like SQL. So, in order to address this issue we have developed an algorithm to efficiently map Amharic language into Structured Query Language (SQL). We divided the algorithm into four parts an algorithm to handle query selection, an algorithm to handle conditional query, an algorithm to handle aggregation and grouping and ordering queries. The algorithm has been implemented in Java and tasted on Human Resource Management (HRM) database containing Employee, Department and Employee on education tables. The experimental result shows that 91% overall accuracy. However, the system shows better performance in single and multiple conditional query, grouping and ordering query and aggregation functions, it doesn't work with Amharic temporal queries. Further improvement will be done to include temporal queries in ANLIDB.

ITM Web of Conferences

In our everyday lives we require information to accomplish daily tasks. Database is one of the most important sources of information. Database systems have been widely used in data storage and retrieval. However, to extract information from databases, we need to have some knowledge of database languages like SQL. But SQL has predefined structures and format, so it is hard for the non-expert users to formulate the desired query. To override this complexity, we have turned to natural language to retrieve information from database, which can be an ideal channel between a non-technical user and the application. But the application cannot understand natural language so an interface is required. This interface is capable of converting the user’s natural language query to an equivalent database language query. In this paper, we address the system architecture for translating a Hindi sentence in the form of an audio to an equivalent SQL query. The users don’t need to learn any formal query ...

Automatically mapping natural language into programming language semantics has always been a major and interesting challenge. Furthermore, as now almost all IT applications are storing and retrieving information from database. Thus retrieving information form the database requires knowledge of technical languages such as Structured Query Language. Moreover most of the users who interact with databases has no knowledge or are not form any technical environment. This has led us to develop the Natural Language Interface for Database where a user from any background is able to query his/her information using natural language. Asking question to databases to in natural Language is very convenient and easy approach of data access from user points of view. Therefore we are developing a Natural Language Interface for Database which will take the query in natural language and automatically map the NL sentence to respective query and show results.

Social Science Research Network, 2021

Database management system has been widely used for storing and retrieving data. However, database is often hard to access the data since their interface is rigid in cooperating with user, due to that analysis of natural language query interface to relational databases has gained much interest in research community. This can be termed as structured free query interface as it allows the users to retrieve the data from the database without knowing the underlying schema. Structured free query interface should address majorly two problems. Querying the system with natural language interfaces is comfortable for the naive users but it is difficult for the machine to understand. The other problem is that the users can query the system with different expressions to retrieve the same information. The different words used in the query can have same meaning and the same word can have multiple meanings. Hence; it is the responsibilities of the NLI to understand the exact meaning of the word in ...