List down the global resources applicable for query expansion, what are the resources useful for query expansion or query reformulation, how does query expansion is achieved? global method for improving recall of an information retrieval system

Question:

List down the common resources for query reformulation / expansion

Answer:

Query expansion is a global method for query reformulation. It is used for adding related words to a query in order to increase the number of returned documents and improve recall accordingly. It often referred as “global query expansion”. As the method uses global resources such as thesaurus and query logs that are not usually query dependent, it is referred to as “global query expansion”. Query expansion uses the following global resources for query reformulation;

1. Controlled vocabulary

There is a canonical term for each concept; all other terms for the same concept are replaced by the canonical term

2. Manual thesaurus

Human annotators build sets of synonymous terms for concepts. Example: PubMed.

3. Automatically generated thesaurus

Attempt to generate a thesaurus automatically by analyzing the distribution of words in documents

4. Query log mining

Query logs are maintained by each search engine in order to analyze the behavior of the user while interacting with search engine. These kind of approaches use these query logs to analyze the user’s preference and adds corresponding terms to query.

Related links/sources

How to improve the recall of an information retrieval system

List down the local methods for improving recall of IR systems

Machine learning multiple choices questions with detailed answers - home page

What are the problems/disadvantages with Jaccard similarity coefficient?

What are the components of a benchmark data collection?

What are the drawbacks of Boolean retrieval model?

What are the drawbacks of relevance feedback in improving search results

Common preprocessing steps and their significance in information retrieval

Keywords

Query expansion techniques

Query expansion methods in information retrieval

Query expansion techniques for question answering

Query expansion to improve document retrieval

Global query expansion how to do

Global methods for improving recall of an IR system

Improve the effectiveness of information retrieval

Global option for improving the recall

What is global query expansion?

Why query expansion is referred to as global method?

How to improve the recall of an IR system, what are the different methods available to improve the search recall? State the global method and local method for effective recall.

Question:

How to increase recall in information retrieval?

Answer:

Recall is the fraction of relevant documents that are retrieved. By modifying the initial query, we can improve the recall. This can be done as follows;

1. By adding new terms to the original query terms that are semantically related to the terms of the original query. This is referred as global method.

2. By making the query vector more similar to vectors of relevant documents. We need some indication of relevance either provided by the user or assumed by the model. This approach is referred as local method.

Related links/questions