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 Plus annual

Presents the access of premium content as premium feature

Premium Content

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 Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Natural language processing (NLP) models trained on people-generated data canbe unreliable because, without any constraints, they can learn from spuriouscorrelations that are not relevant to the task. We hypothesize that enrichingmodels with speaker information in a controlled, educated way can guide them topick up on relevant inductive biases. For the speaker-driven task of predictingcode-switching points in English--Spanish bilingual dialogues, we show thatadding sociolinguistically-grounded speaker features as prepended promptssignificantly improves accuracy. We find that by adding influential phrases tothe input, speaker-informed models learn useful and explainable linguisticinformation. To our knowledge, we are the first to incorporate speakercharacteristics in a neural model for code-switching, and more generally, takea step towards developing transparent, personalized models that use speakerinformation in a controlled way.

Speaker Information Can Guide Models to Better Inductive Biases: A Case Study On Predicting Code-Switching