Glossary Clustering for Accessible Question Answering
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Deep question and answering systems require users to have background knowledge to formulate effective queries, limiting accessibility for users unfamiliar with a subject, as they typically rely on factoid-based answers and do not provide general background information effectively.
Innovation Solution
A method and system that extracts terms and their glossary entries from documents, forms clusters based on similarity algorithms, and ranks these clusters to provide general background information in response to general queries, allowing users to receive pointers to domain terms and formulate suitable questions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If deep question and answering systems rely on factoid-based answers, then answer precision is improved, but user accessibility deteriorates because users need background knowledge to formulate effective queries
Solution Approach 1:
The patent introduces an intermediary component that automatically generates glossary terms and definitions from the document corpus. This intermediary system bridges the gap between the document content and user queries by creating a vocabulary layer that users can leverage to formulate questions without needing domain expertise. The generated glossary serves as a mediator that translates general user intent into domain-specific terminology.
Solution Approach 2:
The system performs preliminary action by pre-generating glossary terms and definitions from the document collection before users arrive. This advance preparation creates a ready-to-use vocabulary resource that users can immediately access to formulate their queries. The glossary is prepared in advance, eliminating the need for users to perform the complex task of domain term extraction themselves.
2Ease of operation
If the system provides general background information, then user accessibility is improved, but information relevance may deteriorate without effective query formulation
Solution Approach 1:
The system enables self-service by allowing users to automatically generate their own glossary terms and definitions by simply providing a document or text. The system then uses these user-provided materials to create personalized glossary entries that are inherently relevant to the user's information needs. This self-service approach ensures that the background information provided is both accessible and relevant to the specific user context.
Solution Approach 2:
The system applies parameter changes by dynamically adjusting the glossary generation process based on user input parameters such as the provided document, desired number of terms, and specific topics of interest. By changing these parameters, the system tailors the generated glossary to maintain high information relevance while preserving ease of access for users with varying levels of domain knowledge.
Data Source
AI summary
A method, system, and computer-usable medium are disclosed for answering general background questions on a topic from documents with glossary sections, A set of documents with glossaries is received from which a set of terms and associated glossary entries are extracted, where each term has a corresponding glossary entry. Association is performed of related glossary entries. The associations is based on a similarity algorithm to form glossary clusters where each glossary cluster refers to one or more glossary entries. A query with query terms tailored to general information is received. The glossary clusters are ranked relevance to the query terms to form a ranked set. A set of glossary clusters meeting a high ranked threshold is selected and provided.