Code-switched Language Models Using Dual RNNs and Same-Source Pretraining [article]

Saurabh Garg, Tanmay Parekh, Preethi Jyothi
2018 arXiv   pre-print
This work focuses on building language models (LMs) for code-switched text. We propose two techniques that significantly improve these LMs: 1) A novel recurrent neural network unit with dual components that focus on each language in the code-switched text separately 2) Pretraining the LM using synthetic text from a generative model estimated using the training data. We demonstrate the effectiveness of our proposed techniques by reporting perplexities on a Mandarin-English task and derive significant reductions in perplexity.
arXiv:1809.01962v1 fatcat:qnd3rvvwf5gmnk3oovjxiqaude