A Sequential and Intensive Weighted Language Modeling Scheme for Multi-Task Learning-Based Natural Language Understanding

A Sequential and Intensive Weighted Language Modeling Scheme for Multi-Task Learning-Based Natural Language Understanding

Multi-task learning (MTL) approaches are actively used for various natural language processing (NLP) tasks. The Multi-Task Deep Neural Network (MT-DNN) has contributed significantly to improving the performance of natural language understanding (NLU) tasks. However, one drawback is that confusion ab...

Full description

Bibliographic Details
Main Authors: Suhyune Son, Seonjeong Hwang, Sohyeun Bae, Soo Jun Park, Jang-Hwan Choi
Format: Article
Language:English
Published: MDPI AG 2021-03-01
Series:Applied Sciences
Subjects:
language modeling
natural language understanding
neural networks
multi-task learning
supervised learning
Online Access:https://www.mdpi.com/2076-3417/11/7/3095

Internet

https://www.mdpi.com/2076-3417/11/7/3095

Similar Items