Strategies of Code-switching in Human-Machine Dialogs

TL;DR

This study explores code-switching strategies in human-machine dialogs using a bilingual chatbot, revealing that predictable code-switching enhances user experience and task success, and demonstrating the research potential of multilingual technology.

Contribution

It introduces a chatbot capable of controlled code-switching in Spanish-English, enabling investigation of bilingual language patterns and user responses in dialog systems.

Findings

Participants preferred predictable code-switching behavior.

Ungrammatical or random code-switching reduced task success.

The approach shows potential for bilingual language research.

Abstract

Most people are multilingual, and most multilinguals code-switch, yet the characteristics of code-switched language are not fully understood. We developed a chatbot capable of completing a Map Task with human participants using code-switched Spanish and English. In two experiments, we prompted the bot to code-switch according to different strategies, examining (1) the feasibility of such experiments for investigating bilingual language use, and (2) whether participants would be sensitive to variations in discourse and grammatical patterns. Participants generally enjoyed code-switching with our bot as long as it produced predictable code-switching behavior; when code-switching was random or ungrammatical (as when producing unattested incongruent mixed-language noun phrases, such as `la fork'), participants enjoyed the task less and were less successful at completing it. These results underscore the potential downsides of deploying insufficiently developed multilingual language technology, while also illustrating the promise of such technology for conducting research on bilingual language use.