A Comparative Study of Intent Classification Performance in Truncated Consumer Communication using GPT-Neo and GPT-2

Computer Science

• Natural Language Processing 100%
• Classification Performance 100%
• Machine Learning Technique 50%
• Language Modeling 50%
• False Negative 50%
• Text Summarization 50%
• Neural Network Architecture 50%
• Language Processing 50%
• Processing Model 50%
• Translation (Languages) 50%
• Essential Resource 50%
• Comparative Analysis 50%
• Negative Value 50%

Engineering

• Classification Performance 100%
• Natural Language Processing 100%
• Negative Value 50%
• Retail Market 50%
• Generative Model 50%
• Answering Question 50%
• Neural Network Architecture 50%
• Summarization 50%
• Comparative Analysis 50%
• Machine Learning Technique 50%
• False Negative 50%

Earth and Planetary Sciences

• Natural Language Processing 100%
• Machine Learning 50%