17934029. DETECTION OF VERACITY OF RESPONSES IN MACHINE COMPREHENSION QUESTION AND ANSWER MODELS simplified abstract (International Business Machines Corporation)
Contents
- 1 DETECTION OF VERACITY OF RESPONSES IN MACHINE COMPREHENSION QUESTION AND ANSWER MODELS
- 1.1 Organization Name
- 1.2 Inventor(s)
- 1.3 DETECTION OF VERACITY OF RESPONSES IN MACHINE COMPREHENSION QUESTION AND ANSWER MODELS - A simplified explanation of the abstract
- 1.4 Simplified Explanation
- 1.5 Potential Applications
- 1.6 Problems Solved
- 1.7 Benefits
- 1.8 Potential Commercial Applications
- 1.9 Possible Prior Art
- 1.10 Unanswered Questions
- 1.11 Original Abstract Submitted
DETECTION OF VERACITY OF RESPONSES IN MACHINE COMPREHENSION QUESTION AND ANSWER MODELS
Organization Name
International Business Machines Corporation
Inventor(s)
Kunal Sawarkar of Franklin Park NJ (US)
Shivam Raj Solanki of Austin TX (US)
DETECTION OF VERACITY OF RESPONSES IN MACHINE COMPREHENSION QUESTION AND ANSWER MODELS - A simplified explanation of the abstract
This abstract first appeared for US patent application 17934029 titled 'DETECTION OF VERACITY OF RESPONSES IN MACHINE COMPREHENSION QUESTION AND ANSWER MODELS
Simplified Explanation
The patent application abstract describes a system for determining the veracity of answers generated by machine comprehension question and answer models. The system involves altering a text corpus to produce altered text corpora, extracting additional answers from the altered text corpora, and comparing these answers to determine a veracity score for the original answer.
- Machine comprehension question and answer models
- Text corpus alteration component
- Veracity score determination based on comparisons
Potential Applications
This technology could be applied in:
- Fact-checking systems
- Automated content verification tools
Problems Solved
This technology addresses:
- Ensuring accuracy of machine-generated answers
- Improving reliability of information retrieval systems
Benefits
The benefits of this technology include:
- Enhancing trust in machine comprehension systems
- Streamlining the verification process for generated answers
Potential Commercial Applications
A potential commercial application for this technology could be:
- Integration into search engines for improved answer accuracy
Possible Prior Art
One possible prior art for this technology could be:
- Existing fact-checking algorithms and systems
Unanswered Questions
How does this technology handle ambiguous answers?
The system may struggle with ambiguous answers that could have multiple interpretations. Further research may be needed to address this issue.
What impact does the alteration of the text corpus have on the accuracy of the answers?
It is unclear how altering the text corpus multiple times may affect the accuracy of the answers generated by the machine comprehension component. Further testing and analysis may be necessary to determine the optimal approach.
Original Abstract Submitted
One or more systems, devices, computer program products and/or computer-implemented methods provided herein relate to determining veracity of answers generated by machine comprehension question and answer models. According to an embodiment, a machine comprehension component can generate a first answer to a query by extracting the first answer from a passage of text corpus. The text corpus alteration component can alter the text corpus one or more times to produce one or more altered text corpora. The machine comprehension component can further extract one or more additional answers to the query from the altered text corpora. A comparison component can determine a veracity score for the first answer based on one or more comparisons of the first answer with the one or more additional answers.