Query Answer Selection Using Pseudo-Queries
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current query answering systems often rely on a single searcher, either strong or weak, which limits the quality of answers provided, as strong searchers do not share their retrieval algorithms or indices, while weak searchers lack access to effective corpora and use simpler algorithms.
Innovation Solution
A method that retrieves both strong and weak searcher answers, generates pseudo-queries using strong searcher answers for weak searchers, and determines quality predictors to select the best answers based on quality and relevance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a strong searcher is used to provide high quality answers, then answer accuracy is improved, but the retrieval algorithm and index are not accessible to public
Solution Approach 1:
The patent introduces pseudo-query answers as an intermediary mechanism. Strong searcher answers are used to generate pseudo-queries that are then submitted to weak searchers. This mediator approach allows the system to leverage both the high accuracy of strong searchers and the accessibility of weak searchers, resolving the contradiction between answer quality and system accessibility.
2Adaptability or versatility
If a weak searcher is used to allow public access to retrieval algorithm and index, then accessibility is improved, but answer quality deteriorates
Solution Approach 1:
The patent merges the strengths of both strong and weak searchers by combining their answers. The system retrieves answers from both searcher types, evaluates their quality using quality predictors, and selects the best answers. This combination approach allows public access to weak searcher algorithms while maintaining high answer quality through strong searcher contributions.
3Measurement precision
If both strong and weak searcher answers are retrieved and compared, then answer selection quality is improved, but system complexity increases
Solution Approach 1:
The patent changes the evaluation parameter from direct answer comparison to quality predictor comparison. Instead of complex semantic analysis of answers, the system uses quality predictors (such as answer length, keyword match quality, and source reliability) to evaluate and compare answers from different searchers. This parameter transformation simplifies the comparison process while maintaining selection quality.
Data Source
AI summary
A tool for determining a query answer selection. The tool receives one or more queries. The tool retrieves one or more strong searcher answers and one or more weak searcher answers, wherein the one or more strong searcher answers are provided by one or more strong searcher engines and the one or more weak searcher answers are provided by one or more weak searcher engines. The tool determines one or more pseudo-query answers, wherein determining the one or more pseudo-query answers includes utilizing the one or more strong searcher answers as a query to the one or more weak searcher engines. Responsive to determining one or more quality predictors, the tool determines whether at least one of the one or more quality predictors for the one or more pseudo-query answers exceeds at least one of the one or more quality predictors for the one or more weak searcher answers.