CMPS 561 Projects

1
CMPS 561 Projects

• Zonghuan Wu, Shixian Chu, Jinfeng Chen

2
Agenda

• Project Topics
• Introduction to IE
• Introduction to TreeMap
• Contacts

3
Topics

• Use GATE to Extract and/or use Treemap to
  visualize Web Data
• Sports data
• Entertainment data
• HTML document
• Recipes
• Financial data
• Coupons
• Or, any interesting field (approval needed)

4
Challenges

• Define Your Topics
• Find data sources
• Online Databases IMDB, http//www.databasesports.
  com/
• Data Dumps (wikipedia, open directory project)
• Forums (coupons, recipes)
• Feeds (e.g. http//finance.yahoo.com/rssindex)
• Crawler (e.g. http//crawler.archive.org/)
• Information Extraction
• GATE
• HTML Parser (htmlparser.sourceforge.net)
• Information Visualization
• Treemap (http//www.cs.umd.edu/hcil/treemap/)

5
Treemap based Search Result Visualization
6
Ben Shneiderman and HCIL
7
Treemap Prior Arts
8
Treemap Prior Arts
9
Treemap - Prior Arts
People can analyze, compare and identify
information 25-50 faster using treemaps versus
tables people prefer treemaps to tables in
subjective ratings including ease-of-use,
clarity, and usefulness and people can learn to
use treemaps quickly without any training.
10
Treemap - Prior Arts
11
Treemap - Prior Arts
12
Treemap - Prior Arts

• Circular Treemap

13
Treemap Prior Arts
14
Treemap Prior Arts
15
Treemap Prior Arts
16
Treemap Prior Arts
17
IE

• Information Extraction (IE) is a technology based
  on analyzing natural language in order to extract
  snippets of information.
• The process takes texts (and sometimes speech) as
  input and produces fixed-format, unambiguous data
  as output.
• This data may be used directly for display to
  users, or may be stored in a database or
  spreadsheet for later analysis, or may be used
  for indexing purposes in Information Retrieval
  (IR) applications such as Internet search engines
  like Google.

18
IE vs. IR

• Function
• an IR system finds relevant texts and presents
  them to the user
• an IE application analyses texts and presents
  only the specific information from them that the
  user is interested in.
• Pros and Cons
• More difficult, knowledge-intensive to build,
  tied to particular domains and scenarios
• More computationally intensive
• Potentially more efficient because of reducing
  the amount of time for people reading

19
Types of IE

• Named Entity recognition (NE)
• Finds and classifies names, places, etc.
• Coreference resolution (CO)
• Identifies identity relations between entities.
• Template Element construction (TE)
• Adds descriptive information to NE results (using
  CO).
• Template Relation construction (TR)
• Finds relations between TE entities.
• Scenario Template production (ST)
• Fits TE and TR results into specified event
  scenarios.

20
Types of IE Examples

• The shiny red rocket was fired on Tuesday. It is
  the brainchild of Dr. Big Head. Dr. Head is a
  staff scientist at We Build Rockets Inc.
• NE, finding entities rocket, Tuesday, Dr. Head
  and We Build Rockets Inc.
• CO, which entities and references (such as
  pronouns) refer to the same thing it refers to
  the rocket.
• TE, what attributes entities have the rocket is
  shiny red and that it is Heads brainchild.
• TR, what relationships between entities there
  are Dr. Head works for We Build Rockets Inc.
• ST, about events that the entities participate in
  there was a rocket launching event in which the
  various entities were involved.

21
(No Transcript)
22
(No Transcript)
23
Contact

• Shixian Chu shixianchu_at_gmail.com
• or sxc1825_at_cacs.louisiana.edu
  
• Jinfeng Chen
• jxc5466_at_cacs.louisiana.edu
• Zonghuan Wu
• 482-1667,
• zwu_at_cacs.louisiana.edu
• ACTR 206

24
Manipulate Wikipedia with JWPL

• http//www.ukp.tu-darmstadt.de/software/jwpl/
• Ali Elshaimaa E eea7236_at_cacs.louisiana.edu
• Zonghuan Wu zwu_at_cacs.louisiana.edu