Documentos de Académico
Documentos de Profesional
Documentos de Cultura
---------------------------------------------------------------------***---------------------------------------------------------------------
Abstract - Information is playing an important role in day- Marathi, Bengali, Arabic etc. in situ of formal query language
to-day life. This database technology has the major impact on which may be excellent interface between Associate in
the growing use of computer and internet. Database Nursing application of laptop and non-technical user.
management system has been used for accessing, storing and
retrieving data. However, database system is not 1.1 Natural Language Processing (NLP)
understandable to each and every user because they are hard
to use and understand. People dont have the knowledge of Natural language processing (NLP) is a field of computer
database language may find it difficult to access database. science, artificial intelligence, and computational linguistics
However, information system isn't intelligible to every and concerned with the interactions between computers and
each user as a result of they're arduous to use and perceive.
human (natural) languages. As such, NLP is related to the
individuals with no information of Database language might
realize it tough to access information. Therefore, there's got to area of humancomputer interaction. In theory, informatics
establish the new technique and strategies to access the could be a terribly enticing technique of human laptop
information with the employment of tongue process. so this interaction. Linguistic component understanding is usually
idea of victimization tongue, SQL triggered the event of a remarked as Associate in Nursing AI-complete downside as a
special variety of process methodology referred to as tongue result of it appears to need an intensive information
Interface to information wherever user doesn't have needing regarding the surface world and therefore the ability to
to be told the formal language, they will offer question in their
control it. Informatics has considerably overlapped with the
linguistic communication. For the those who area unit comfy
with the Hindi language would like this application to just sphere of computational linguistics, and is commonly
accept Hindi sentence as a question , method it and once thought of a sub-field of computing. NLP has significantly
execution offer result to the user within the same language overlapped with the field of computational linguistics, and is
that is nothing however the Hindi Language Interface to often considered a sub-field of artificial intelligence.
direction System.
Key Words: DBMS, HLIDBMS, NLP, NLIDB, SQL. The foundation of natural language processing lies during a
variety of disciplines like pc and data sciences, linguistics,
arithmetic, electrical and EE, computing and AI,
1. INTRODUCTION psychological, agriculture, prognostication etc. [1].
Applications of natural language processing embrace variety
of fields of studies, like artificial intelligence, language
The requirement of information and data is very important
interface to information, language text process and report,
part of life. There are various sources of information but the
user interfaces, polyglot and cross language data retrieval
major one is the databases. Database helps us to store, access
(CLIR), speech recognition, AI and professional system, and
and retrieve information. There area unit numerous sources
so on.
of knowledge however the foremost one is that the
databases. Information helps North American nation to
store, access and retrieve info. every and each laptop 1.2 Natural Language Interface to Database
applications area unit dependable on information to access (NLIDB)
the knowledge. For that it's necessary to own information of
formal query language like SQL however it's terribly A person with no knowledge of database language may find
troublesome for everybody to find out and write SQL it difficult to access database easily. Therefore, SQL tutor was
queries. to beat this downside several scientist have brought developed for analyzing the ability of Natural Language
bent on use linguistic communication (NL) i.e. English, Hindi, Processing to develop products for people to interact with
2017, IRJET | Impact Factor value: 5.181 | ISO 9001:2008 Certified Journal | Page 1293
International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395 -0056
Volume: 04 Issue: 03 | Mar -2017 www.irjet.net p-ISSN: 2395-0072
database in simple English. These, product have created a 2.3 RENDEZVOUS System
revolution in extracting data from databases. they need In the system developed and studied by E. Codd [8] users
discarded the excessive of learning SQL and time is could access databases via relatively
additionally saved in learning in query language. unrestricted natural language. In this Codes system, special
emphasis is placed on query paraphrasing and in engaging
users in clarification dialogs when there is difficulty in
2. RELATED WORK
parsing user input.
Work for developing NLIDB has started in early seventies.
2.4 PLANES
Since then many systems have been developed. Early
D. Waltz stated [9] the Programmed Language-based
systems have many flaws then some systems were
Enquiry System (PLANES) at the University of Illinois
developed to overcome these flaws. Some of the developed
Coordinated Science Laboratory. PLANES include an English
NLIDB systems are discussed below.
language front end with the ability to understand and
Following are some developed NLIDB systems are given- explicitly answer user requests. It carries out clarifying
dialogues with the user as well as answer vague or poorly
2.1 LUNAR System defined questions. This work is being carried out using
W. Woods etal [5] has given information about LUNAR database based upon information of the U.S. Navy 3-M
system that answers questions about samples of rocks Maintenance and Material Management, it is a database of
brought back from the moon. The meaning of systems name aircraft maintenance and flight data, although the ideas can
is that is in relation to the moon. To accomplish its function be directly applied to other non-hierarchic record based
the LUNAR system uses two databases; one for the chemical databases.
analysis and the other for literature references. The LUNAR
2.5 PHILIQA
system uses an Augmented Transition Network (ATN)
This was known as Philips Question Answering System
parser and Woods Procedural Semantics. W. Woods [6]
(PHILIQA) explained by R. Scha [10], uses a syntactic parser
have also given the study of the LUNAR system performance
which runs as a separate pass from the semantic
which was quite impressive; it managed to handle 78% of
understanding passes. This system is mainly involved with
requests without any errors and this ratio rose to 90% when
problems of semantics and has three separate layers of
dictionary errors were corrected. But these figures may be
semantic understanding. The layers are called "English
misleading because the system was not subject to intensive
Formal Language", "World Model Language", and "Data Base
use due to the limitation of its linguistic capabilities.
Language" and appear to correspond roughly to the
2.2 LADDER "external", "conceptual", and "internal" views of data.
It was designed as a NLIDB of information about US Navy
2.6 CHAT-80
ships. According to G. Hendrix etal [7], the LADDER system
. CHAT-80 was implemented entirely in Prolog and it is the
uses semantic grammar to parse questions to query a
best NLIDBs system. It transformed English questions into
distributed database. Although semantic grammars helped to
Prolog expressions, which were evaluated against the Prolog
implement systems with impressive characteristics, the
database. The code of CHAT-80 was circulated widely and
resulting systems proved difficult to port to different
formed the basis of several other experimental NLIDBs. The
application domains. Indeed, a different grammar had to be
database of CHAT-80 consists of facts (i.e. oceans, major
developed whenever LADDER was configured for a new
seas, major rivers and major cities) about 150 of the
application [5]. The system uses semantic grammars
countries world and a small set of English language
technique that interleaves syntactic and semantic
vocabulary that are enough for querying the database [24] .
processing. The question answering is done via parsing the
input and mapping the parse tree to a database query. The
2.7 TEAM
system LADDER was implemented in LISP. At the time of
B. J. Gross has given a paper on TEAM
creation of the LADDER system, it was able to process a
database that is equivalent to a relational database with 14 (Transportable Natural Language Interface system). A large
tables and 100 attributes. part of the research of that time was devoted to portability
issues. TEAM was designed to be easily configurable by
2017, IRJET | Impact Factor value: 5.181 | ISO 9001:2008 Certified Journal | Page 1294
International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395 -0056
Volume: 04 Issue: 03 | Mar -2017 www.irjet.net p-ISSN: 2395-0072
database administrators with no knowledge of NLIDBs [11, enforce problem areas or introduce new query concepts
12]. [22].
2.10 EUFID
M.Templeton etal [14] has given that the EUFID system
3. PROPOSED SYSTEM
consists of three major modules, not counting the DBMS.
3.1. Problem Statement
First is analyzer module, second is mapped module and
Hindi language interface to online database is totally
third is translator module.
supported the foundations through that we have a tendency
2.11 DATALOG to area unit reaching to perform the operations like choose,
It is an English database query system based on Cascaded insert, update, delete. We have a tendency to are operating to
ATN grammar. By providing separate representation produce the advance question operation like practicality of
schemes for linguistic knowledge, general 14 world mixture functions like MIN (), MAX (), SUM () and AVG ().
knowledge, and application domain knowledge, DATALOG The user can sort the question in Hindi language which
achieves a high degree of portability and extendibility [15]. language has been processed and can offer the output in
Systems that also appeared in mid-eighties were LDC [16], Hindi language solely. Time distinction has been calculated,
TQA [17], TELI [18] and many others. system can offer translation time and execution time in
milliseconds further as in nanoseconds.
2.12 SQL Tutor
SQL can be very difficult for beginner users to understand. 3.2. Methodology
The SQL-Tutor program tutors students by assisting the To achieve the above objective methodology used is given as
students through a number of database questions from four we are going to use the rule based system which will follow
different databases. A student model is kept for each student and execute each and every query as per the rules made for
based on query constraints (each constraint represents a it. First it will identify the nature of the query i.e. select,
part of the query that is necessary to answer the question). update, delete, create, insert and also it will identify that the
Each time a particular query constraint is used, SQL-Tutor query is with aggregation functions or not. To achieve the
records whether it was used successfully or unsuccessfully. higher than objective methodology used is given as- we tend
In this way a model of a students strengths and weaknesses to area unit reaching to use the rule based mostly system
is generated and SQL-Tutor can select questions which re- which can follow and execute every and each question as per
2017, IRJET | Impact Factor value: 5.181 | ISO 9001:2008 Certified Journal | Page 1295
International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395 -0056
Volume: 04 Issue: 03 | Mar -2017 www.irjet.net p-ISSN: 2395-0072
Figure1. Architecture
2017, IRJET | Impact Factor value: 5.181 | ISO 9001:2008 Certified Journal | Page 1296
International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395 -0056
Volume: 04 Issue: 03 | Mar -2017 www.irjet.net p-ISSN: 2395-0072
Aggregate function will identify whether it is min (), max (), during conversion and same in the case of execution time
sum (), avg () query or not . Other rules like where clause for also, it will show the time required to execute the query.
that are given the properties i.e. It will identify all the
associated Hindi English words which are given below in the
fig 3. 4. CONCLUSIONS
Similarly where condition is also there it will work like same REFERENCES
as given above it is consisting of all the conditional part and
[1] Amandeep Kaur, Punjabi Language Interface to
its associated Hindi words including <,>,=,logical and ,or not Database, ME Thesis, Thapar University, Jun 2010.
etc. [2] H. R. Tennant, K. M. Ross, M. Saenz, C.W. Thompson and
J.R. Miller, Menu Based Natural Language
Similarly for update query it is having update column rule Understanding, Proceeding of the 21st Annual Meeting
,where clause rule and where condition rule and its working of ACL, Cambridge, Massachusetts, pp. 151-158, 1993.
is same as explained above. The same way insert and delete [3] W. Woods, R. Kaplan and B. Webber, B., The Lunar
Sciences Natural Language Information System, Final
also work. Report. B. B. N. Report No 2378, USA, 1972.
[4] W. Woods, An experimental parsing system for
At last there is query generator which will generate query transition network grammars. In Natural Language
from Hindi sentence .that query generated will be fired to Processing, Algorithmic Press, New York, USA, 1973.
database and all the selected records selected rows has been [5] G. Hendrix, E. Sacrdoti, D. Sagalowicz, and J. Slocum,
Developing a natural language interface to complex
displayed in Hindi Language. SQL is generated in this phase data, ACM Transactions on Database Systems, Volume
according to Hindi sentence. Execute query and display 3, No. 2, pp. 105 147, USA, 1978.
result to user the above SQL query is executed and result of [6] E.F. Codd, Seven steps to rendezvous with the casual
which in Hindi language is displayed to user. The output is in user, In IFIP Working Conference Data Base
Management, pp 179200, 1974.
the form of Hindi language and we are giving query also in
[7] [9] D.L. Waltz., An English Language Question
Hindi language and processing of all this has been done by Answering System for a Large Relational Database,
fig.1 as explained above. Communications of the ACM, pp 526 539, 21(7): July
1978.
[8] R.J.H. Scha., Philips Question Answering System
PHILIQA1, In SIGART Newsletter, no.61. ACM, New
York, February 1977.
[9] B.J. Grosz, TEAM: A Transportable Natural-Language
Interface System, In Proceedings of the 1st Conference
Figure4. GUI & timing results on Applied Natural Language Processing, Santa Monica,
California, pp 3945, 1983.
Once the query has been executed and the result has been [10] B.J. Grosz, D.E. Appelt, P.A. Martin, and F.C.N. Pereira,
shown it will also show the timing result which include TEAM: An Experiment in the Design of Transportable
whether the query has been successfully executed or not if it Natural-Language Interfaces, Artificial Intelligence, pp
173243, 32: (1987).
is failed it will show the unsuccessful message as shown in
the fig4. It will also give the translation time in milliseconds [11] P. Resnik, Access to Multiple Underlying Systems in
JANUS, BBN report 7142, Bolt Beranek and Newman
as well as nanoseconds to notice the minute difference Inc., Cambridge, Massachusetts, September 1989.
2017, IRJET | Impact Factor value: 5.181 | ISO 9001:2008 Certified Journal | Page 1297
International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395 -0056
Volume: 04 Issue: 03 | Mar -2017 www.irjet.net p-ISSN: 2395-0072
2017, IRJET | Impact Factor value: 5.181 | ISO 9001:2008 Certified Journal | Page 1298