Agenda for Presenation

Download Report

Transcript Agenda for Presenation

Agenda for Presenation
 What is NLIDB
 What has been done
 What is to be done
What is NLIDB?




Organized Data
Questions and Answers
Use of SQL
Basically, we are trying to extract
data present in SQL databases
What is the BIG idea?
 Correspondence between
relationships and verbs (or
Adjectives)
 Concept of verb frames to represent
the relationships
 What is a verb frame???
 A frame with a central verb and some
arguments
How does this idea work?
 Some information we need to provide
to the NLIDB
 Understanding the database
 The different verb frames present
 How this information is presented?
 The 5 files that the developer needs to
make
ER representation

Example Format













%er_rep = {
student => {
type => 'entity' ,
attribute => [
Student_ID,Name,Date_OF_Birth,Email,Sex,Address,City,State,Pin,Sex,
CGPA,Program_
Name,Year_Of_Admission ] ,
primary_key => 'Student_ID' ,
rel_ship => 'register'
},
registration => {
type => 'relationship' ,
attribute => [
Student_ID,Course_Code,Course_Grade ],
primary_key => 'Student_ID,Course_Code' ,
entity => 'student,course_offering'
}
Verb Frames
 Example Format
NLexpr=STUDENT$ GET GRADE$ IN COURSE$
ERexpr=register(student._key_,course_offering.gra
de,course_offering._key_)
NL-Er_Mapping=
Verb::GET;
SUBJ::STUDENT$::student._key_;
OBJ::GRADE$::registration.Course_Grade;
PP_IN::COURSE$::course_offering.Course_Name;
Definitions
 Example Format
STUDENT$=pupil,student;
GRADE$=grade,marks,percentage;
Join Information
 Example Format
faculty:course_offering=>FACULTY.Faculty_
ID=COURSE_OFFERING.Faculty_ID
Course_offering:registration=>COURSE_OF
FERING.Course_Code=REGISTRATION.C
ourse_Code
registration:student=>STUDENT.Student_I
D=REGISTRATION.Student_ID
Database Information
 Example Format:
IP Address of Database Server =
172.16.9.26
Database Name = academics
UserName = root
Password = nlidb123
What all can the system do?
 Understand simple sentences
 Understand alternatives of nouns
used
 Understand alternatives of verbs used
 Come up with a probable answer
What can it be made to do?
 A lot of things
 Handle complex sentences (Nested
Queries)
 Simple Dialog Modeling (A project on
Semantic Completion is done)
 Improved Adjectives Handling
Non NLP stuff which can be done
 Distribution mechanism for different
domain/database data
 Improving database search
 Different DBMS
The End
 Questions?