Natural Language Inference for Intent Determination
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Traditional natural language model training for determining user intent in electronic systems requires large amounts of labeled training data, which is costly in terms of time and money.
Innovation Solution
The system uses a small amount of labeled training data and employs natural language inference to determine user intent by comparing user input with stored example expressions, leveraging a natural language inference model to compute scores and select the most applicable intent, with the option to reverse-score if initial confidence is insufficient.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional natural language model training is used to determine user intent, then the system can achieve reliable intent determination, but it requires large amounts of labeled training data which is costly in terms of time and money
Solution Approach 1:
The patent introduces natural language inference as an intermediary mechanism between user input and intent determination. Instead of directly training a model on large labeled datasets, the system uses NLI to compare user expressions against stored example expressions and derive intent through semantic inference, thereby reducing the need for extensive labeled training data while maintaining determination reliability
Solution Approach 2:
The system performs preliminary actions by pre-storing example natural language expressions for each intent in a database before actual user interactions. These pre-prepared examples serve as reference points that enable the NLI model to infer user intent without requiring real-time access to large training datasets, thus reducing the quantity of labeled data needed during deployment
Data Source
AI summary
An online system that allows users to interact with it using expressions in natural language form includes an intent inference module allowing it to infer an intent represented by a user expression. The intent inference module has a set of possible intents, along with a small set of example natural language expressions known to represent that intent. When a user interacts with the system using a natural language expression for which the intent is not already known, the intent inference module applies a natural language inference model to compute scores indicating whether the user expression textually entails the various example natural language expressions. Based on the scores, the intent inference module determines an intent that is most applicable for the expression. If an intent cannot be determined with sufficient confidence, the intent inference module may further attempt to determine whether the various example natural language expressions textually entail the user expression.