Center for Computational Learning Systems

1
Center for Computational Learning Systems

• Independent research center within the
  Engineering School
• NLP people at CCLS Mona Diab, Nizar Habash,
  Martin Jansche, Rebecca Passonneau, Owen Rambow
• What we do
• Researchers
• Work with Kathy and Julia
• Our own projects
• Sometimes teach
• Supervise students (PhD, Masters, independent
  studies)
• Some of us are in CEPSR, some in the Interchurch
  Building
• Some NLP Group meetings will take place in
  Interchurch Center

2
CLiMB 2 Computational Linguistics for Metadata
Building, phase 2

• Becky Passonneau (with University of Maryland)
• Interactive workbench for image
  cataloguers/indexers Use NLP to extract
  descriptive terms from scholarly text
• Mellon Foundation
• http//www.umiacs.umd.edu/climb/

3
Automated Readers Advisor, Heiskell Talking Books
and Braille Library (NYPL)

• Becky Passonneau
• Replace some of librarians tasks in current
  over-the-phone borrowing sytem with automated
  dialogue system
• Use Wizard-of-Oz paradigm for data collection
• Joint project with CCNY (Esther Levin)
• http//www.cs.columbia.edu/becky/pubs/WozVariant.
  ppt

4
Tracking Emergent Narrative Skills (TENS)

• Becky Passonneau
• Current data set ten-year olds retelling silent
  movies
• Develop quantitative methods to compare semantic
  and pragmatic content (e.g., adapt Pyramid Method
  for evaluating summary content)
• Joint project with University of Connecticut
  (Elena Levy)

5
Arabic NLP

• CADIM Group Mona Diab, Nizar Habash, Owen Rambow
• Focus on Standard Arabic AND the dialects
• NLP tools for Arabic
• Morphological analysis (exists)
• Morphological tagging (exists, best-performing)
• Tokenization
• POS tagging (best-performing)
• Diacritization (best-performing)
• Word-sense disambiguation (in progress)
• Sentence-boundary detection for ASR (in progress)
• Parsing (initial research)
• Names-entity recognition (joint with Fair Isaacs,
  in progress)

6
Machine Translation

• Nizar Habash
• Focus Arabic-English MT
• Different hybrid MT approaches explored
• Linguistic preprocessing for Statistical MT
• Morphological and Syntactic preprocessing
• Adding statistical resources to rule-based MT
  systems
• Automatically extracted phrase tables combined
  with Generation-Heavy MT
• Columbia first time participation in NIST MTEval
  (2006)

7
Word Sense Modeling and Disambiguation

• Mona Diab
• Using corpora (including multilingual parallel
  and similar) for unsupervised learning
• Arabic WordNet
• Arabic PropBank

8
Multilingual Metagrammars

• Owen Rambow (with University of Pennsylvania)
• Goal high-level abstract representation of
  syntax of (many/all) natural languages, from
  which we can automatically generate grammars that
  can be used for NLP
• Have Universal Grammar component and
  language-specific modules for Korean, German,
  Yiddish
• Next Icelandic, Mainland Scandinavian, English,
  Kashmiri,