Information Extraction and Retrieval - IIIT Hyderabad

More documents

Recommendations

Info

Classic IR Models - Basic Concepts • Each document represented by a set of representative keywords or index terms • An index term is a document word useful for remembering the document main themes • Index terms may be selected to be only nouns, since nouns have meaning by themselves – Should reduce the size of the index – ... But it requires the identification of nouns Part of Speech tagger • However, search engines assume that all words are index terms (full text representation) 20
Classic IR Models - Basic Concepts • Not all terms are equally useful for representing the document contents: less frequent terms allow identifying a narrower set of documents • The importance of the index terms is represented by weights associated to them • Let – k i be an index term – d j be a document – w ij is a weight associated with (k i ,d j ) • The weight w ij quantifies the importance of the index term for describing the document contents 21
Page 1 and 2: IR Systems (Note: Many slides from
Page 3 and 4: Approaches to IR Two types of
Page 5 and 6: Typical IR Task Given: Find: A
Page 7 and 8: Web Search System Web Spider Docume
Page 9 and 10: Keyword Search Simplest notion of
Page 11 and 12: Relevant items are similar Much of
Page 13 and 14: How effective is IR? Anecdotal e
Page 15 and 16: Intelligent IR Taking into account
Page 17 and 18: IR System Components Text Operati
Page 19: IR Models Set Theoretic Classic Mod
Page 23 and 24: Drawbacks of the Boolean Model •
Page 25 and 26: Vector-based Model • Define: - w
Page 27 and 28: Vector Based Model • Sim(q,d j )
Page 29 and 30: Probabilistic Model • An initial
Page 31: 31 Thank You - Questions? Vasudeva

Information Extraction and Retrieval - IIIT Hyderabad

You also want an ePaper? Increase the reach of your titles

Delete template?

Save as template?