5.2 Probabilistic Retrieval Example
The documents set contain four documents with following contents:
The indexed documents have been presented in the Figure 1.4. The terms are extracted from the documents. Term weight is applied to each term. The weight of each term is calculated and it can be used in the same way as the IDF vector in the Vector Space Model.
Figure 1.4: Example of documents representation for PIR
After term weights are calculated, the relevance values can be calculated for each of the documents.