Scribd
Upload
6 views1 page

IR Experiment 5

The document outlines an experiment on query expansion techniques to enhance retrieval performance in Information Retrieval systems. It describes two types of query expansion: Local (using relevance feedback from top-ranked documents) and Global (using external knowledge sources). The procedure includes dataset preparation, initial query execution, query expansion, re-running the query, and evaluating precision and recall before and after expansion.

Uploaded by

purswanijiten11
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
6 views1 page

IR Experiment 5

The document outlines an experiment on query expansion techniques to enhance retrieval performance in Information Retrieval systems. It describes two types of query expansion: Local (using relevance feedback from top-ranked documents) and Global (using external knowledge sources). The procedure includes dataset preparation, initial query execution, query expansion, re-running the query, and evaluating precision and recall before and after expansion.

Uploaded by

purswanijiten11
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd

Experiment 5

Title: To execute a query expansion technique (Local or Global) to improve retrieval


performance in an Information Retrieval system.

Theory:

Query Expansion (QE) is the process of reformulating a user’s query by adding


related terms to improve retrieval effectiveness. It helps overcome vocabulary
mismatches between queries and documents.

There are two main types of query expansion:

1.​ Local Query Expansion (Relevance Feedback):


○​ Expansion terms are selected from the top-ranked documents retrieved
in an initial search.
○​ Example: Rocchio algorithm modifies the original query vector based
on relevant documents.​

2.​ Global Query Expansion (Thesaurus-Based):


○​ Expansion terms are derived from external knowledge sources such as
thesauri, ontologies, or word embeddings.​

○​ Example: Expanding “car” with “automobile,” “vehicle,” etc.

Procedure:

1.​ Dataset Preparation:


○​ Use a small text corpus (20 documents).
2.​ Initial Query Execution:
○​ Input a query and retrieve top results without expansion.
3.​ Query Expansion:
○​ Local: Use terms from top retrieved documents to expand the query.
○​ Global: Use synonyms or related terms from a thesaurus or WordNet.
4.​ Re-run Query:
○​ Execute the expanded query and retrieve results again.
5.​ Evaluation:
○​ Compare precision and recall before and after query expansion.

Conclusion:

●​ Summary of Observations.

You might also like