Information-Retrieval-Scoring-Models

This poject contains implementations of two key document ranking models used in Information Retrieval (IR):

• BM25/Okapi: A probabilistic ranking function based on term frequency, document length normalization, and inverse document frequency.
• Binary Independence Model (BIM): A probabilistic model assuming independence between query terms and used to score and rank documents based on binary term presence.

Project Workflow:

• Tokenization of documents
• BM25 scoring and ranking (configurable parameters: k=1.5, b=0.75)
• BIM scoring with support for a set of query terms
• Outputs ranked list of documents with corresponding relevance scores

Dataset

A sample set of documents and a query are used to test the models:

• Query: "information retrieval models"
• Documents: D1 to D8 (provided in the code)