JNTU MCA 2019 INFORMATION RETRIEVAL SYSTEMS Previous Question Paper (April/May - 2019 - R15)

A Biword Index is a technique used to handle phrase queries by indexing pairs of consecutive terms as a single token. Instead of storing individual words, the system stores adjacent word pairs, such as "data mining" or "information retrieval," in the dictionary. This allows for efficient retrieval of multi-word phrases without complex post-processing. For example, the sentence "The quick brown fox" would be indexed as the biwords "the quick," "quick brown," and "brown fox."

Inverse Document Frequency (IDF) measures how much information a word provides, specifically whether it is common or rare across all documents in a collection. It is calculated as the logarithm of the total number of documents divided by the number of documents containing the term. A high IDF value indicates a rare, highly informative term, while a low IDF value indicates a common term that carries less discriminative power for retrieval.

Where N is the total number of documents and df(t) is the number of documents containing term t.