NLU Glossary Module for Nonstandard Term Interpretation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Spoken language processing systems face challenges in interpreting nonstandard terms, such as slang, nicknames, and variable definitions, which can lead to errors and invalid results when these terms are not recognized or are used in unexpected ways.
Innovation Solution
The system employs an NLU module that obtains definitions for nonstandard terms from user-specific data, shared definition data, and unstructured data, and prompts the user for clarification if necessary, while tracking feedback to refine interpretations over time.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If the NLU module uses standard named entity recognition, then processing speed is maintained, but accuracy deteriorates when encountering nonstandard terms like slang, nicknames, and variable definitions
Solution Approach 1:
The patent introduces an intermediary component (glossary or dictionary module) that mediates between the NLU module and nonstandard terms. This intermediary stores predefined mappings between nonstandard terms (slang, nicknames, variable definitions) and their standard meanings, allowing the system to resolve ambiguities without fundamentally redesigning the entire NLU architecture.
Solution Approach 2:
The system performs preliminary actions by pre-defining and storing glossaries of nonstandard terms and their meanings before actual language processing occurs. This advance preparation allows the NLU module to quickly lookup and resolve nonstandard terms during processing without performing complex real-time analysis, thereby improving accuracy while maintaining system simplicity.
2Measurement precision
If the system requests user clarification for nonstandard terms, then interpretation accuracy improves, but user interaction time increases
Solution Approach 1:
The system employs self-service by automatically resolving nonstandard terms through predefined glossaries and contextual analysis without requiring user intervention. The NLU module independently queries stored glossaries, analyzes contextual clues from the conversation, and resolves ambiguities autonomously, eliminating the need for time-consuming user clarification while maintaining high interpretation accuracy.
3Adaptability or versatility
If the NLU module tracks and stores user feedback, then system adaptability improves, but data management complexity increases
Solution Approach 1:
The patent merges the feedback tracking functionality with the existing glossary storage infrastructure. User feedback and learned term definitions are integrated into the same data storage mechanism used for predefined glossaries, allowing the system to adapt and learn new nonstandard terms while utilizing existing data management protocols and storage structures, thereby minimizing additional complexity.
Data Source
AI summary
Features are disclosed for determining a definition or value of a nonstandard term. A user utterance may be processed into one or more candidate transcriptions. An interpretation of the utterance can be generated from the transcriptions. If the transcription includes a word, phrase, or term that is not recognized or is used in a nonstandard way, one or more data stores may be queried regarding the proper value or definition of the term. If a definition or value is not available in the data stores, the user may be prompted to provide one. The user-supplied definition can be saved for future use, and may be used as a general definition of the term for other users.