Strategies of Code-switching in Human-Machine Dialogs
This addresses the challenge of deploying multilingual technology effectively for bilingual users, though it is incremental in exploring specific dialog strategies.
The study tackled the problem of understanding code-switched language in human-machine dialogs by developing a chatbot for a Map Task using Spanish and English, finding that participants enjoyed predictable code-switching but disliked random or ungrammatical patterns, leading to reduced task success.
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.