English

Language Modeling for Code-Switching: Evaluation, Integration of Monolingual Data, and Discriminative Training

Computation and Language 2019-11-12 v3

Abstract

We focus on the problem of language modeling for code-switched language, in the context of automatic speech recognition (ASR). Language modeling for code-switched language is challenging for (at least) three reasons: (1) lack of available large-scale code-switched data for training; (2) lack of a replicable evaluation setup that is ASR directed yet isolates language modeling performance from the other intricacies of the ASR system; and (3) the reliance on generative modeling. We tackle these three issues: we propose an ASR-motivated evaluation setup which is decoupled from an ASR system and the choice of vocabulary, and provide an evaluation dataset for English-Spanish code-switching. This setup lends itself to a discriminative training approach, which we demonstrate to work better than generative language modeling. Finally, we explore a variety of training protocols and verify the effectiveness of training with large amounts of monolingual data followed by fine-tuning with small amounts of code-switched data, for both the generative and discriminative cases.

Keywords

Cite

@article{arxiv.1810.11895,
  title  = {Language Modeling for Code-Switching: Evaluation, Integration of Monolingual Data, and Discriminative Training},
  author = {Hila Gonen and Yoav Goldberg},
  journal= {arXiv preprint arXiv:1810.11895},
  year   = {2019}
}

Comments

EMNLP 2019

R2 v1 2026-06-23T04:55:10.761Z