Auto-creation of custom models for text summarization

US12045272B2 · kind B2 · utility

Assignee

• Adobe Inc. · US

Inventors

• Saurabh Mahapatra · Sunnyvale, US
• Niyati Himanshu Chhaya · Chilpur, IN
• Snehal Raj · Tarasingi, IN
• Sharmila Reddy Nangi · Hyderabad, IN
• Sapthotharan Krishnan Nair · Santa Clara, US
• Sagnik Mukherjee · Sherghati, IN
• Jay Mundra · Bhadesar, IN
• Fan Du · Campbell, US
• Atharv Tyagi · Atrauli, IN
• Aparna Garimella · Hyderabad, IN

Key dates

• Filing date: Jul 8, 2021
• Grant date: Jul 23, 2024
• Expiry date: Jul 22, 2042

Classification

• Technology area (CPC G): Physics
• CPC primary: G06N3/092
• WIPO field: Computer technology
• WIPO sector: Electrical engineering

Abstract

A text summarization system auto-generates text summarization models using a combination of neural architecture search and knowledge distillation. Given an input dataset for generating/training a text summarization model, neural architecture search is used to sample a search space to select a network architecture for the text summarization model. Knowledge distillation includes fine-tuning a language model for a given text summarization task using the input dataset, and using the fine-tuned language model as a teacher model to inform the selection of the network architecture and the training of the text summarization model. Once a text summarization model has been generated, the text summarization model can be used to generate summaries for given text.