English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

We focus on the problem of language modeling for code-switched language, inthe context of automatic speech recognition (ASR). Language modeling forcode-switched language is challenging for (at least) three reasons: (1) lack ofavailable large-scale code-switched data for training; (2) lack of a replicableevaluation setup that is ASR directed yet isolates language modelingperformance from the other intricacies of the ASR system; and (3) the relianceon generative modeling. We tackle these three issues: we propose anASR-motivated evaluation setup which is decoupled from an ASR system and thechoice of vocabulary, and provide an evaluation dataset for English-Spanishcode-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 oftraining with large amounts of monolingual data followed by fine-tuning withsmall amounts of code-switched data, for both the generative and discriminativecases.

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