17519911. COMPUTER ASSISTED ANSWERING BOOLEAN QUESTIONS WITH EVIDENCE simplified abstract (International Business Machines Corporation)

From WikiPatents
Jump to navigation Jump to search

COMPUTER ASSISTED ANSWERING BOOLEAN QUESTIONS WITH EVIDENCE

Organization Name

International Business Machines Corporation

Inventor(s)

Sara Rosenthal of Spring Valley NY (US)

Jeffrey Scott Mccarley of Bedford Hills NY (US)

Mihaela Ancuta Bornea of White Plains NY (US)

COMPUTER ASSISTED ANSWERING BOOLEAN QUESTIONS WITH EVIDENCE - A simplified explanation of the abstract

This abstract first appeared for US patent application 17519911 titled 'COMPUTER ASSISTED ANSWERING BOOLEAN QUESTIONS WITH EVIDENCE

Simplified Explanation

The patent application describes a method for using natural language software on a computing device to respond to Boolean questions. Here are the key points:

  • The computing device receives a question and at least one passage.
  • The question is classified as a Boolean type question.
  • The computing device generates evidence from the passage(s) to answer the Boolean question.
  • The computing device generates a response to the Boolean question using the evidence.
  • The computing device provides the generated evidence that supports the response.

Potential Applications

This technology has various potential applications, including:

  • Question-answering systems: It can be used in chatbots or virtual assistants to provide accurate and efficient responses to Boolean questions.
  • Information retrieval: It can help users find specific information by answering questions with a simple "yes" or "no" response.
  • Decision-making support: It can assist in decision-making processes by quickly providing evidence-based answers to Boolean queries.

Problems Solved

This technology addresses several problems:

  • Efficient response to Boolean questions: It enables computing devices to quickly and accurately respond to Boolean questions, saving time and effort for users.
  • Natural language understanding: It improves the ability of computing devices to understand and interpret natural language queries.
  • Evidence-based responses: It ensures that the generated responses are supported by evidence from the provided passages, enhancing the reliability of the answers.

Benefits

The use of this technology offers several benefits:

  • Improved user experience: Users can receive prompt and accurate responses to Boolean questions, enhancing their overall satisfaction.
  • Time and effort savings: The method allows for efficient retrieval of information, reducing the time and effort required to find answers.
  • Reliable and evidence-based answers: The generated responses are supported by evidence, increasing the trustworthiness of the information provided.


Original Abstract Submitted

A method of using a computing device using natural language software to respond to a Boolean question is presented. The method includes receiving, by a computing device, a question and at least one passage. The computing device classifies the question as a Boolean type question. The computing device generates evidence from the at least one passage to the Boolean question. The computing device generates a response to the Boolean question using the generated evidence. The computing device provides the generated evidence that supports the response to the Boolean question.