2000 character limit reached
Using Chatbots to Teach Languages (2208.00376v1)
Published 31 Jul 2022 in cs.CL and cs.AI
Abstract: This paper reports on progress towards building an online language learning tool to provide learners with conversational experience by using dialog systems as conversation practice partners. Our system can adapt to users' language proficiency on the fly. We also provide automatic grammar error feedback to help users learn from their mistakes. According to our first adopters, our system is entertaining and useful. Furthermore, we will provide the learning technology community a large-scale conversation dataset on language learning and grammar correction. Our next step is to make our system more adaptive to user profile information by using reinforcement learning algorithms.
- Yu Li (377 papers)
- Chun-Yen Chen (5 papers)
- Dian Yu (78 papers)
- Sam Davidson (7 papers)
- Ryan Hou (3 papers)
- Xun Yuan (15 papers)
- Yinghua Tan (2 papers)
- Derek Pham (2 papers)
- Zhou Yu (206 papers)