18545621. DISTANCE-BASED LOGIT VALUE FOR NATURAL LANGUAGE PROCESSING simplified abstract (Oracle International Corporation)

DISTANCE-BASED LOGIT VALUE FOR NATURAL LANGUAGE PROCESSING

Organization Name

Oracle International Corporation

Inventor(s)

Ying Xu of Albion (AU)

Poorya Zaremoodi of Melbourne (AU)

Thanh Tien Vu of Brisbane (AU)

Cong Duy Vu Hoang of Wantirna South (AU)

Vladislav Blinov of Melbourne (AU)

Yu-Heng Hong of Carlton (AU)

Yakupitiyage Don Thanuja Samodhye Dharmasiri of Melbourne (AU)

Vishal Vishnoi of Redwood City CA (US)

Elias Luqman Jalaluddin of Seattle WA (US)

Manish Parekh of San Jose CA (US)

Thanh Long Duong of Pointcook (AU)

Mark Edward Johnson of Castle Cove (AU)

DISTANCE-BASED LOGIT VALUE FOR NATURAL LANGUAGE PROCESSING - A simplified explanation of the abstract

This abstract first appeared for US patent application 18545621 titled 'DISTANCE-BASED LOGIT VALUE FOR NATURAL LANGUAGE PROCESSING

Simplified Explanation

The abstract describes a method for using logit values to classify utterances input to chatbot systems in natural language processing.

• Chatbot system receives user utterance
• Utterance input into machine-learning model with binary classifiers
• Each binary classifier associated with modified logit function
• Model generates distance-based logit values for utterance
• Enhanced activation function applied to logit values for predicted output
• Chatbot system classifies utterance based on predicted output

Potential Applications

This technology could be applied in various chatbot systems to improve the accuracy of classifying user utterances.

Problems Solved

This technology helps chatbot systems better understand and classify user input, leading to more effective communication and responses.

Benefits

- Improved accuracy in classifying user utterances - Enhanced performance of chatbot systems - Better user experience in interacting with chatbots

Potential Commercial Applications

This technology could be utilized in customer service chatbots, virtual assistants, and other conversational AI applications.

Possible Prior Art

One potential prior art could be the use of machine learning models with binary classifiers in natural language processing systems.

How does this method handle multi-class classification in chatbot systems?

The abstract focuses on binary classification, but it is unclear how this method would be adapted for multi-class classification tasks in chatbot systems.

What is the computational complexity of applying the enhanced activation function to a large set of logit values?

The abstract does not provide information on the computational efficiency of the method when dealing with a significant number of logit values in chatbot systems.

Original Abstract Submitted

Techniques for using logit values for classifying utterances and messages input to chatbot systems in natural language processing. A method can include a chatbot system receiving an utterance generated by a user interacting with the chatbot system. The chatbot system can input the utterance into a machine-learning model including a set of binary classifiers. Each binary classifier of the set of binary classifiers can be associated with a modified logit function. The method can also include the machine-learning model using the modified logit function to generate a set of distance-based logit values for the utterance. The method can also include the machine-learning model applying an enhanced activation function to the set of distance-based logit values to generate a predicted output. The method can also include the chatbot system classifying, based on the predicted output, the utterance as being associated with the particular class.