17457445. GENERATION OF QUERY TEMPLATES FOR KNOWLEDGE-GRAPH BASED QUESTION ANSWERING SYSTEM simplified abstract (INTERNATIONAL BUSINESS MACHINES CORPORATION)
GENERATION OF QUERY TEMPLATES FOR KNOWLEDGE-GRAPH BASED QUESTION ANSWERING SYSTEM
Organization Name
INTERNATIONAL BUSINESS MACHINES CORPORATION
Inventor(s)
JIAN MIN Jiang of Beijing (CN)
GENERATION OF QUERY TEMPLATES FOR KNOWLEDGE-GRAPH BASED QUESTION ANSWERING SYSTEM - A simplified explanation of the abstract
This abstract first appeared for US patent application 17457445 titled 'GENERATION OF QUERY TEMPLATES FOR KNOWLEDGE-GRAPH BASED QUESTION ANSWERING SYSTEM
Simplified Explanation
The abstract describes a processor that uses a knowledge graph to generate queries and find answers to questions in natural language. Here are the key points:
- The processor takes a question and answer pair in natural language.
- It identifies entities in the question and determines their entity type based on the knowledge graph schema.
- It generates a subset of candidate query templates based on the entity types.
- The processor creates a set of queries by inserting the entities into the candidate query templates.
- These queries are executed on the knowledge graph to generate answers.
- The processor compares the generated answers with the provided answer and identifies a matching answer.
- It determines the candidate query template corresponding to the matching answer as the final query template.
Potential applications of this technology:
- Question answering systems: This technology can be used to build intelligent systems that can understand and answer questions in natural language.
- Knowledge base querying: It can be used to query large knowledge bases efficiently and accurately.
- Virtual assistants: This technology can enhance virtual assistants by enabling them to provide more accurate and relevant answers to user queries.
Problems solved by this technology:
- Efficient querying: The processor generates queries based on the knowledge graph schema, which helps in retrieving relevant information quickly.
- Accurate answers: By comparing the generated answers with the provided answer, the processor ensures that the final answer is accurate and matches the expected answer.
- Natural language understanding: This technology enables the processor to understand and process questions in natural language, making it easier for users to interact with systems.
Benefits of this technology:
- Automation: The processor automates the process of generating queries and finding answers, reducing the need for manual intervention.
- Improved accuracy: By leveraging the knowledge graph and comparing answers, the technology improves the accuracy of the generated answers.
- Time-saving: The processor quickly generates queries and retrieves answers from the knowledge graph, saving time for users and improving efficiency.
Original Abstract Submitted
A processor obtains a pair including a question and an answer in natural language; determines at least one entity in the question and an entity type of each of the at least one entity consistent with the schema of a knowledge graph (KG); identifies a subset of candidate query templates based on the entity type of each of the at least one entity, wherein the candidate query templates are generated based on the schema of the KG; composes a set of queries by populating the at least one entity into each of the subset of candidate query templates; executes the set of queries on the KG to generate respective answers; identifies a first answer from the respective answers that is matching with the answer in the pair; and determines a candidate query template, from the subset of candidate query templates, corresponding to the first answer as a query template.
