CS5604 Review
Topics
Outline
- Motivation
- Basic human need for information
- Information explosion, growth of literature
- Commercial import of knowledge
- Luhn, Cleverdon, Salton - automatic better than manual
- Evaluation
- Recall and precision: defns, relationship
- Test collections
- TREC
- Averaging
- Statistical significance
- Models
- Boolean
- Vector space
- Indexing process
- Lexical analysis
- Stop words
- Weighting: TF, IDF, DV
- Inverted file
- LSI
- Probabilistic
- Inference
- AI
- NLP
- Expert systems
- Knowledge bases
- Improvements
- Transformations related to frequency
- Recall enhancing devices
- Precision enhancing devices
- Feedback
- Rocchio
- Ide
- Probabilistic
- Estimation
- Contingency table
- Query expansion
- Integration of sources
- Interfaces
- Thesauri
- Phrases
- Multimedia
- Audio: speech, sound
- Images
- Video
- HCI
- Clustering
- Terms
- Documents
- Browsing, linking
- Hypothesis