4. Introduction
Law of Sri Lanka.
Law literacy in the country.
The detailed scope.
Nayana Dharmasiri
5. Background
Serve the people in need of knowing more
about law.
Search engine consist of irrelevant data
regarding law.
Providing a way to get the law information.
Nayana Dharmasiri
7. Literature Review
Research and Development of Search Engines
• First search engine was Archie created by Alan Emtage.
• Web crawler was introduced in 1994.
• Then Lycas became first search engine.
• Later on Google became the first in the market.
Research and Development of Natural Language Processing
• Field concerned with interaction between computer and human
languages.
• Alan Turing published computing machinery and intelligence article.
• Georgetown experiment in 1954 on translating Russian sentences into
English.
• Late research on unsupervised and semi managed learning calculation.
Umavi Pathirana
Nayana Dharmasiri
8. Comparison through Literature Review
System
Function Google Search
Engine
Yahoo Search Engine Law and Order Search
Engine
Information With Simple
Words. X X
Details of particular lawyers
for existing law areas. X X
Consist of all cases
categorized according to
particular law areas.
X X
Consist of all law reports
categorized according to
particular law areas.
X X
Umavi Pathirana
9. Solution
Providing a unique search engine specially for law
Providing all law cases, law report and law conventions
Providing law conventions in simple English
Providing steps to handle particular situations
User Friendly Search Results
Providing convenient data taken from the Law Commission
Committee
Umavi Pathirana
10. System High level Diagram
Original Document
Documents with Simple form
of data
Search Engine
Information Extraction
Information
Retrieval
Searching
User
Result
Umavi Pathirana
13. Information Extraction
• Information Extraction Methods
Utilize Artificial Intelligence Strategies.
Machine Learning Calculations.
• Information Extraction Techniques
Syntactic rules.
Fundamental natural language processing
techniques.
Sajani Senevirathne
14. Sentence
segmentation
Tokenization
Part of speech tagging
Entity detection
Relation detection
Raw text
(string)
Sentences
(list of string)
Tokenized sentences
(list of lists of string)
POS-tagged sentences
(list of lists of tuples)
Chunked sentences
(list of trees)
Relations
(list of tuples)
Information Extraction
Sajani Senevirathne
15. Information Retrieval
• Retrieve Information
• Full text Indexing
Numeric scoring
• Obtaining information from file system
Sajani Senevirathne
16. Methods used for Information Retrieval
• Topic based smoothing.
• Relevance models.
• Translation based models.
Sajani Senevirathne
24. Business Model
Key Activities Value Propositions Customer Segments
Key Resources
Cost Structure
Managing law
information
Providing
information in
simple form
Conventions
Law reports
Law cases
File server cost
Web search
OS and
platforms
Android, iOS
Internet Users
Lawyers
Law Students
Bashitha Guanthilake
25. Significance
This study will be mainly beneficial to the lawyers and
law students
Lawyers and law students can be assured of a
significant advantage.
Significant aspire in making it easy to search anything
about the law for the citizens.
serve as a future reference for researchers on the
subject of producing a search engine.
Bashitha Guanthilake