Extracting Academic Affiliations Status Report

1
Extracting Academic AffiliationsStatus Report

• Alicia Tribble
• Einat Minkov
• Andy Schlaikjer
• Laura Kieras

2
The Problem

• Identify people who are affiliated with an
  academic institution
• Degrees earned
• Positions held (student, post-doc, faculty)
• Current position
• Class of beliefs to be learned
• affiliated(ltpersongt,ltdegreegt,ltinstitutiongt)

3
The System /Algorithm
Query Generator
Search EngineInterface
Query relation
Query pattern
Html files
Extract patterns
Extract relations
Patterns
Relations (facts)
Assess patterns
Assess relations
4
Algorithm Details

• Pattern query formulation
• Replace ltarggt in pattern string with '' operator
• Remove leading and trailing ''s
• Wrap query string in quotes
• Example
• "ltPERSONgt received his ltDEGREEgt from
  ltUNIVERSITYgt"
• -becomes-
• '"received his from"'

5
Algorithm Details

• Relation Extraction (Slot filling)
• Find the relevant sentence/s on a page
• Alignment slot filling
• Some cleanup he, capitalization
• Examples
• Robertson, Ph.D. in ecology and evolutionary
  biology, Indiana University
• Jeff, B.S., Bucknell University
• Rex Jung, degree, University of New Mexico
• Alavosius, BA in psychology, Clark University
• Jacobs, B.E.E. degree, Cornell University
• He, Associates Degree in Livestock Production,
  Northeast Community College

6
Algorithm Details

• Relation query formulation
• All argument values become query terms
• Example
• (William Cohen, Ph.D., Rutgers)
• -becomes-
• 'William Cohen Ph.D. Rutgers'

7
Algorithm Details

• Pattern Extraction
• Build a regex from a relation, one per argument
• (Mr\.MrMRM\.?r\.?Dr\.?Mrs\.?MRSMsMS)
  ?(Scott FahlmanScottFahlman)
• (a-zA-Z? dDegreeDdoctoral
  DdegreePhDPh\.D\.DoctoratePHD)
• (MIT)
• Apply regex to input and for every match, extract
  intermediate string and generalize
• ltPERSONgt received her ltDEGREEgt from ltUNIVERSITYgt
• ltPERSONgt received his ltDEGREEgt from ltUNIVERSITYgt
• ltPERSONgt earned a ltDEGREEgt from ltUNIVERSITYgt
• ltPERSONgts, MD ltUNIVERSITYgt

8
Experimental Settings

• Initial seeds
• Relations
• affiliated('William Cohen', 'Ph.D.', 'Duke
  University')
• affiliated('Tom Mitchell', 'Ph.D.', 'Stanford')
• affiliated('Scott Fahlman', 'Ph.D.', 'MIT')
• Patterns
• ltPERSONgt received his ltDEGREEgt from ltUNIVERSITYgt
• ltPERSONgt earned his ltDEGREEgt from ltUNIVERSITYgt
• ltPERSONgt earned a ltDEGREEgt from ltUNIVERSITYgt
• Testing and development performed with 2
  bootstrap iterations, using only Google snippets

9
Results!

• inital
• patterns 3
• relations 3
• iteration 0
• patterns 6 (3)
• relations 13 (3)

• iteration 1
• patterns 14 (9)
• relations 0
• total
• patterns 23
• relations 16

10
Interim Conclusions

• Issue I over-specificity of queries arguments
• Q "Oren Etzioni" "Ph.D" "CMU"
• But, what if actual relevant mention
  includesA "Oren Etzioni", "doctorate"
  "Carnegie Mellon University".. ?
• Possible avenues
• Larger dictionaries
• Unquote query arguments? (allow for some
  variation)
• Allow argument values to include random terms
  "Oren Etzioni"
• This might incorporate more noise, and require
  additional queries to be issued per relation.

11
Interim Conclusions

• Issue II name and pronoun resolution
• Q "Oren Etzioni" "Ph.D" "CMU"
• But, what if actual relevant mention
  includesA "He recieved his Ph.D from CMU
  in..."
• Rate of occurance of "S/he..." in extracted
  relations
• 1 pattern, 50 queries 56.8 (96/169)
• Possible avenues
• Identify homepages and extract names from titles,
  or other unambiguous sources on page
• Pronoun resolution simple techniques?? (for
  example, identify immediate previous name
  mentions. This may require NER.)

12
Interim Conclusions

• Issue III compound sentences
• Q "Oren Etzioni" "Ph.D" "CMU"
• But, what if actual relevant mention
  includesA "Oren Etzioni recieved his MS from
  ltUNIVERSITYgt, and his Ph.D from CMU"
• Possible avenues
• Extensions to pattern extraction techinque
• May require dependency parsing

13
Software / Resources

• A generic search framework which allows
  asynchronous processing of search tasks, as well
  as "filter" tasks (processing of resulting URLs)
• A URL caching implementation of Java 1.5's
  java.net.ResponseCache using Hibernate,
  supporting centralized caching and remote access

14
Generic Search Framework
Search
Extraction
SearchProcessor
Search
Test run 1 Search50 URLs169 Extractions15
seconds
Search Tasks
Filter Tasks
Result
Filter
15
Search Framework System Flow
16
Extensions

• Dictionaries - next slide
• Simple pronoun resolution
• Extraction validation metrics
• URL of professors personal home page
• Clustering of people / universities, or
  normalization of names
• Identify biography section of personal home pages
• Links incoming and outgoing from personal home
  page

17
Additional information

• Dictionary of institution names
• Tiny dictionary of degrees
• E.g. Ph.D., B.S., B. Tech., etc
• Map of domain names to institution names
• E.g. cmu.edu Carnegie Mellon University
• This could be learned but we will leave that for
  another group!

18
Example extracted relations

• Dictionary of institution names
• Tiny dictionary of degrees
• E.g. Ph.D., B.S., B. Tech., etc
• Map of domain names to institution names
• E.g. cmu.edu Carnegie Mellon University
• This could be learned but we will leave that for
  another group!