Conversational agents for learning foreign languages -- a survey

TL;DR

This survey reviews the current state of conversational agents used for language learning, analyzing their capabilities, challenges, and potential for improving informal language practice.

Contribution

It provides a comprehensive overview and critical analysis of existing chatbot approaches for language learning, highlighting key challenges and future directions.

Findings

Chatbots can enhance motivation and engagement in language learners.

Current chatbots have limited conversational capabilities for effective language practice.

Major challenges include improving naturalness and contextual understanding.

Abstract

Conversational practice, while crucial for all language learners, can be challenging to get enough of and very expensive. Chatbots are computer programs developed to engage in conversations with humans. They are designed as software avatars with limited, but growing conversational capability. The most natural and potentially powerful application of chatbots is in line with their fundamental nature - language practice. However, their role and outcomes within (in)formal language learning are currently tangential at best. Existing research in the area has generally focused on chatbots' comprehensibility and the motivation they inspire in their users. In this paper, we provide an overview of the chatbots for learning languages, critically analyze existing approaches, and discuss the major challenges for future work.