1. Home
2. Premium
3. IEEE ICASSP 2020 Virtual Conference May 2020
4. Integrating Discrete And Neural Features Via Mixed-Feature Trans-Dimensional Random Field Language Models

Integrating Discrete And Neural Features Via Mixed-Feature Trans-Dimensional Random Field Language Models

Collection:

IEEE ICASSP 2020 Virtual Conference May 2020

There has been a long recognition that discrete features (n-gram features) and neural network based features have complementary strengths for language models (LMs). Improved performance can be obtained by model interpolation, which is, however, a sub-opti

• IEEE MemberUS $11.00
• Society MemberUS $0.00
• IEEE Student MemberUS $11.00
• Non-IEEE MemberUS $15.00

Purchase

Videos in this product

Integrating Discrete And Neural Features Via Mixed-Feature Trans-Dimensional Random Field Language Models

00:14:23

0 views

There has been a long recognition that discrete features (n-gram features) and neural network based features have complementary strengths for language models (LMs). Improved performance can be obtained by model interpolation, which is, however, a sub-opti