Paper

Word Predictability on Code-switching Points in Cantonese–English Discourse

---

Abstract

This paper investigates how word predictability influences code-switching probability. We analyze 1,010 code-switched instances drawn from naturalistic sociolinguistic interviews with 41 Cantonese--English bilinguals across three bilingual groups (homeland, immersed, and heritage). In particular, we examine whether the predictability of switch points, operationalized as surprisal, influences the likelihood of code-switching. Using pretrained transformer-based language models, we estimate surprisal at the switch point under different modeling conditions, including autoregressive and masked models and varying amounts of contextual information. Mixed-effects logistic regression analyses show that less predictable words are more likely to be code-switched. These effects are largely consistent across model types and bilingual groups. Overall, these findings highlight the role of predictability in bilingual speech production and provide new insights into code-switching among bilingual speakers with diverse language experiences.

Keywords: Code-switching, Word Predictability, Bilingualism, Linguistics, Corpus Analysis, Language Modeling

How to Cite:

Chan, A., Li, Y. & Poschl, J., (2026) “Word Predictability on Code-switching Points in Cantonese–English Discourse”, Society for Computation in Linguistics 9(1). doi: https://doi.org/10.7275/scil.4059