Code Switching Language Model Using Monolingual Training Data
This work provides an incremental improvement for researchers and developers working on code-switching language models, particularly in scenarios where code-switched training data is scarce.
This paper addresses the challenge of training a code-switching language model using only monolingual data. The authors trained an RNN language model using alternate batches of English and Spanish monolingual data, which reduced perplexity from 299.63 to 80.38 when combined with mean square error in output embeddings.
Training a code-switching (CS) language model using only monolingual data is still an ongoing research problem. In this paper, a CS language model is trained using only monolingual training data. As recurrent neural network (RNN) models are best suited for predicting sequential data. In this work, an RNN language model is trained using alternate batches from only monolingual English and Spanish data and the perplexity of the language model is computed. From the results, it is concluded that using alternate batches of monolingual data in training reduced the perplexity of a CS language model. The results were consistently improved using mean square error (MSE) in the output embeddings of RNN based language model. By combining both methods, perplexity is reduced from 299.63 to 80.38. The proposed methods were comparable to the language model fine tune with code-switch training data.