InterviewBot: Real-Time End-to-End Dialogue System for Interviewing Students for College Admission

Abstract

We present the InterviewBot, which dynamically integrates conversation history and customized topics into a coherent embedding space to conduct 10 min hybrid-domain (open and closed) conversations with foreign students applying to U.S. colleges to assess their academic and cultural readiness. To build a neural-based end-to-end dialogue model, 7361 audio recordings of human-to-human interviews are automatically transcribed, where 440 are manually corrected for finetuning and evaluation. To overcome the input/output size limit of a transformer-based encoder–decoder model, two new methods are proposed, context attention and topic storing, allowing the model to make relevant and consistent interactions. Our final model is tested both statistically by comparing its responses to the interview data and dynamically by inviting professional interviewers and various students to interact with it in real-time, finding it highly satisfactory in fluency and context awareness.