1. Home
2. Premium
3. IEEE ICASSP 2020 Virtual Conference May 2020
4. Training Code-Switching Language Model With Monolingual Data

Training Code-Switching Language Model With Monolingual Data

Collection:

IEEE ICASSP 2020 Virtual Conference May 2020

A lack of code-switching data complicates the training of code-switching (CS) language models. We propose an approach to train such CS language models on monolingual data only. By constraining and normalizing the output projection matrix in RNN-based lang

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

Purchase

Videos in this product

Training Code-Switching Language Model With Monolingual Data

00:12:05

0 views

A lack of code-switching data complicates the training of code-switching (CS) language models. We propose an approach to train such CS language models on monolingual data only. By constraining and normalizing the output projection matrix in RNN-based lang