Iterative Query Expansion Modules for Information Retrieval
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In digital computer systems, initial user information is often incomplete, making it challenging to accurately perform downstream classification tasks or database inquiries, particularly in applications like decision support systems for risk stratification, where additional information is needed to identify missing key aspects.
Innovation Solution
A method for query expansion that involves receiving a current query, inputting search terms into query expansion modules to predict candidate expansion terms, modifying the query using these terms, and repeating the process until a predefined stopping criterion is met, thereby refining the query to improve information retrieval.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If query expansion is performed using multiple modules and iterative refinement, then query accuracy and information retrieval quality improve, but system complexity and processing time increase
Solution Approach 1:
The query expansion system is divided into multiple independent query expansion modules, each responsible for generating candidate expansion terms from different perspectives or sources. This segmentation allows the system to improve query accuracy through diverse expansion strategies while maintaining modularity that manages system complexity.
Solution Approach 2:
The system performs preliminary query expansion by generating candidate terms before final query execution. Multiple rounds of expansion are performed iteratively, with each round refining the query further. This preliminary action approach allows thorough query refinement while structuring the complexity in a manageable sequential process.
2Measurement precision
If iterative query refinement is performed multiple times, then query-document mismatch is minimized and retrieval quality improves, but processing time increases
Solution Approach 1:
The system implements iterative query refinement where each expansion round uses feedback from previous rounds to further improve the query. The process repeats until a stopping criterion is met, allowing the system to balance retrieval quality improvement against processing time by dynamically determining when sufficient refinement has been achieved.
Solution Approach 2:
The system performs multiple rounds of query expansion beyond what a single pass would provide, applying excessive action to ensure thorough refinement. The iterative process with stopping criteria allows the system to achieve high retrieval quality while preventing unlimited processing by knowing when to stop the refinement cycles.
Data Source
AI summary
The present disclosure relates to a method for query expansion. The method comprises: a) receiving a current query having at least one search term; b) inputting the at least one search term of the current query to a set of one or more query expansion modules, wherein the query expansion modules are configured to predict expansion terms of input terms; c) receiving from the set of expansion modules candidate expansion terms of the search term; d) modifying the current query using at least part of the candidate expansion terms, resulting in a modified query having at least one modified search term, The method further comprises repeating steps b) to d) using the modified query as the current query, the repeating being performed until a predefined stopping criterion is fulfilled.