@inproceedings{garg-etal-2018-code,
    title = "Code-switched Language Models Using Dual {RNN}s and Same-Source Pretraining",
    author = "Garg, Saurabh  and
      Parekh, Tanmay  and
      Jyothi, Preethi",
    editor = "Riloff, Ellen  and
      Chiang, David  and
      Hockenmaier, Julia  and
      Tsujii, Jun{'}ichi",
    booktitle = "Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing",
    month = oct # "-" # nov,
    year = "2018",
    address = "Brussels, Belgium",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/add-emnlp-2024-awards/D18-1346/",
    doi = "10.18653/v1/D18-1346",
    pages = "3078--3083",
    abstract = "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."
}