Conversational Agent for Daily Living Assessment Coaching [conference paper]

Conference

AI4Function Workshop, International Joint Conference on Artificial Intelligence (IJCAI) - January 7, 2021

Authors

Aditya Gaydhani (M.S. student), Raymond Finzel, Sheena Dufresne, Maria Gini (professor), Serguei Pakhomov

Abstract

We present preliminary work-in-progress results of a project focused on developing a conversational agent system to help with training certified assessors in conducting assessments of functioning in activities of daily living. To date, we have designed a modular task-based conversational agent system and collected hypothetical dialogue data required for training system components as well as a knowledge base needed to generate a wide variety of synthetic profiles of “individuals” being assessed. One of the key components of the system is the topic tracking module that determines the current topic of the conversation. We report the results of experiments with several machine learning approaches to topic/domain classification. The highest accuracy of 83% was achieved with a bidirectional long short-term memory (BiLSTM) model with pre-trained GloVe embeddings. In addition to these results, we also discuss some of the other challenges that we have encountered so far and potential solutions that we are currently pursuing.

Link to full paper

Conversational Agent for Daily Living Assessment Coaching

Keywords

intelligent agents