Despite their pervasiveness, current text-based conversational agents (chatbots) are predominantly monolingual, while users are often multilingual. It is well-known that multilingual users mix languages while interacting with fellow humans as well as with computer systems such as query formulation in text or voice-based search interfaces and digital assistants. Linguists refer to this phenomenon as code-mixing code-switching. Do multilingual users also prefer chatbots that can respond in a code-mixed language over those which cannot? In this talk, I will discuss a mixed-method user-study where we examined how conversational agents that code-mix and reciprocate the users’ mixing choices over multiple conversation turns are evaluated and perceived by bilingual users. A human-in-the-loop chatbot was implemented with two different code-mixing policies – (a) always code-mix irrespective of user behavior, and (b) nudge with subtle code-mixed cues and reciprocate only if the user, in turn, code-mixes. These two were contrasted with a monolingual chatbot that never code-mixed. Users were asked to interact with the bots, and provide naturalness and preference ratings. They were also asked open-ended questions around what they (dis)liked about the bots. Analysis of the chat logs, and users’ preference ratings and qualitative responses reveal that multilingual users strongly prefer chatbots that can code-mix. We find that self-reported language proficiency is the strongest predictor of user preference. Compared to the Always code-mix policy, Nudging emerges as a low-risk low-gain policy which is equally acceptable to all users. Nudging as a policy is further supported by the observation that users who rate the code-mixing bot higher typically tend to reciprocate the language mixing pattern of the bot.
Please give your valuable feedback https://docs.google.com/forms/d/e/1FAIpQLSc5iTuHPm6RRWFdRt6EOO22eClhCiFYHW4E4TsXq2zKICoGhQ/viewform?usp=sf_link And here’s the bio I normally use: Kalika Bali is a Principal Researcher at Microsoft Research India working broadly in the area of Speech and Language Technology especially in the use of linguistic models for building technology that offers a more natural Human-Computer as well as Computer-Mediated interactions, and technology for Low Resource Languages. She has been working in the field of Speech and Natural Language Processing for over two decades and believes that local language technology especially with speech interfaces, can help millions of people gain entry into a world that is till now almost inaccessible to them.