Progress Report Related work in KM

1
Progress Report Related work in KM

• Advisor Prof. Hahn-Ming Lee
• Prof. Jan-Ming Ho
• Reporter Shou-Wei Ho
• Chung-Hung Lin
• 2009.08.31

2
Related work in KM (Knowledge Management)
3
Problems in searching Chinese(??) name
Only Chinese Corpus
4
Challenges in Chinese name translation

• Many pronunciation rules in different areas
• ? ? Chen (Taiwan)
• ? ? Tsun (Hong Kong)
• ? ? Tan (Fukien)
• Some additional words exist.
• Ex ??? (Kwang-Ming Frank Hwang)
• Ex ??? (Jane Win-Shih Liu)

5
Ambiguous pages in the WWW(??)
CMU Professor
Guitar Player and Singer
?
6
Anchor text mapping
1.
3.
2.
1.
2.
B. NVIDIA web site page
3.
Search Name Bill Mark
A. Personal main page
7
CRE Why do we extract information from
publication list web page? (??)

• Publication list page is an important resource
  for many value-added applications, such as
  citation analysis and academic network analysis.
• What could we get from publication list pages?
• Some up-to-date literatures before they are
  formally published
• Some reference materials, such as slides and
  talks.

8
An automatic extractor
Citation String
Web Page
Extract
Detect 3 relationships cont.
Detect 3 relationships cont.
Structure Data
9
Citation extracting
10
Authorship Disambiguation(??)
?
?
Prof. A
Prof. A
11
Detect 3 relationships(COI)

• 1. Teacher-Student

Prof. A
Prof. B
Student C
12
Detect 3 relationships cont.

• 2. Co-author

Prof. A
Prof. S
13
Detect 3 relationships cont.

• 3. Colleagues

Prof. E
Prof. A
Prof. W
14
Mining a Chinese Persons Name from the English
Translation(??)
15
(No Transcript)
16
Name Disambiguation(??)

• Problem
• Given a set of citations with the same author
  name, how do we identify which one belongs to
  whom?
• Goal
• To group the citations into several clusters, so
  that each cluster represents an author

17
Procedure
18
Procedure

• Use classification result to group citations into
  several clusters
• Each cluster contains citations belonging to the
  same author

Grouping
If SVM determines two citations are authored by
the same person, then they are connected each
other
19
Citation Correspondence(??)

• Query construction
• A good query
• If proper records are achieved in digital
  libraries, good query should get them in search
  result, at the same time, proper records should
  have higher ranking.
• Search result should be small.
• Citation correspondence
• Find proper records from search result by
  matching local citation string and records in
  search result.
• Field-by-field comparison.
• May be not enough due to errors in digital
  libraries (optional).
• Metrics precision, recall, and F-measure.

20
Partial Solution Abbreviation Matching
v1
v2
Example CIKM Conference on Information and
Knowledge Management
21
Reviewer Recommendation(??)
22
COI in incomplete collaboration Network via
social Interaction(??)