Num
Hoor Qadri
Nisreen Al-Saleh



Idea
I
D
E
A



Solved Problems
Find the number quickly.

Heuristic.

Real-time.




Our Aim





Find the numbers quickly


Target Market




Students
Journalists
Researchers
Business Companies











Project Timeline

	Sep	Oct	Nov	Dec	Jan	Feb	Mar	Apr	May
									



Software Engineering

NLP 
Analysis & documenting 
Backend process
Frontend process
Interface
Indexing
Crawling


Project flowchart



Crawling

Study of Web Crawler and its Different Types [1]








Text data
 












Preprocessing 
Clean Text


Name Entity Recognition(Gate)

Advantages:
Supports Arabic Language

Disadvantages:
Lack of resources
Not easy to learn

Gate tool[2]


Advantages:
Extract entities (Location , Person ,Organization and numbers).

Disadvantages:
Hard to recognize the chunks of the data.

Example:
Text : An-Najah National University
 Results : An-Najah: Org , National: Org , University: Org


Name Entity Recognition(Stanford)
Stanford[3]



11

Advantages:
Extract entities (Location , Person ,Organization, Phone,Emails,URLs,Percentages,Product,Money and Keywords).

Can recognize the chunks of the data.

Disadvantages:
Can’t make more than 60 request per minute.
Can’t make more than 1000 call per day.




Name Entity Recognition(AYLIEN)


Name Entity Recognition tools Combination 
Aylien
LOC
ORG
PER
Keywords

Stanford 

NER
NUM


IRS

Lucene flow[4]


 
2
 
3
 
Choose appropriate crawling library
1
Page structures
Choose appropriate NLP tool
Challenges 


Acknowledgment 



Dr.Abed Razzaq Natsheh 
Dr.Hamed Abdelhaq
Mr.Omar Rayyan


References 
[1] Trupti V. Udapure , Ravindra D. Kale , Rajesh C. Dharmik, “Study of Web Crawler and its Different Types”, IOSR Journal of Computer Engineering (IOSR-JCE), Volume 16, Issue 1, Ver. VI (Feb. 2014).
[2] Gate general architecture for text engineering , https://gate.ac.uk/
[3] The Stanford Natural Language Processing Group, https://nlp.stanford.edu/software/
[4]Lucene flow,  http://gopaldas.org/wp-content/uploads/2015/10/lucence-flow.png








ANY QUESTIONS
?
?
?


image2.jpeg

image3.png

image4.png

image5.png

image6.png

image7.jpeg

image8.png

image9.png

image10.png

image1.jpeg


/docProps/thumbnail.jpeg