17457479. STOP WORD DETECTION FOR QA CORPUS simplified abstract (INTERNATIONAL BUSINESS MACHINES CORPORATION)
Contents
STOP WORD DETECTION FOR QA CORPUS
Organization Name
INTERNATIONAL BUSINESS MACHINES CORPORATION
Inventor(s)
STOP WORD DETECTION FOR QA CORPUS - A simplified explanation of the abstract
This abstract first appeared for US patent application 17457479 titled 'STOP WORD DETECTION FOR QA CORPUS
Simplified Explanation
The abstract of this patent application describes a method for generating dependency trees for questions and answers in a question answering system. The method involves identifying root nodes in the dependency trees and comparing words near these root nodes to words in the associated answers. If a word appears in less than a certain number of associated answers, it is considered a stop word.
- Dependency trees are generated for questions and answers in a question answering system.
- Root nodes in the dependency trees are identified.
- Words near the identified root nodes of questions are compared to words in the associated answers.
- Words appearing in less than a threshold number of associated answers are identified as stop words.
Potential Applications
- Question answering systems
- Natural language processing
- Information retrieval
Problems Solved
- Improving the accuracy of question answering systems
- Enhancing the understanding of question-answer relationships
- Identifying irrelevant words in questions and answers
Benefits
- More accurate and efficient question answering
- Improved understanding of the context and meaning of questions and answers
- Reduction of noise and irrelevant information in question answering systems
Original Abstract Submitted
Dependency trees are generated for questions and answers of a question answering (QA) corpus in which the answers are associated with the questions. Generating the dependency trees includes identifying root nodes. A word near an identified root node of one of the questions is compared to words of answers associated with the one of the questions. The word is determined to be in less than a threshold number of the associated answers. The word is identified as a stop word.