Abstract

Conversational Agent for Daily Living Assessment Coaching (CADLAC) is a multi-modal conversational agent system designed to impersonate “individuals” with various levels of ability in activities of daily living (ADLs: e.g., dressing, bathing, mobility, etc.) for use in training professional assessors how to conduct interviews to determine one’s level of functioning. The system is implemented on the MindMeld platform for conversational AI and features a Bidirectional Long Short-Term Memory topic tracker that allows the agent to navigate conversations spanning 18 different ADL domains, a dialogue manager that interfaces with a database of over 10,000 historical ADL assessments, a rule-based Natural Language Generation (NLG) module, and a pre-trained open-domain conversational sub-agent (based on GPT-2) for handling conversation turns outside of the 18 ADL domains. CADLAC is delivered via state-of-the-art web frameworks to handle multiple conversations and users simultaneously and is enabled with voice interface. The paper includes a description of the system design and evaluation of individual components followed by a brief discussion of current limitations and next steps.

Highlights

  • A person’s ability to function independently in everyday life depends on multiple factors including, but not limited to, intact physical and mental capacity

  • We used two sources of data in order to inform Conversational Agent for Daily Living Assessment Coaching (CADLAC) system design, train machine learning models, and to develop a database to support rulebased approaches used by the system

  • The assessors were asked to recall some of their past assessments and provide examples of interactions that they had with people during the assessment interviews

Read more

Summary

Introduction

A person’s ability to function independently in everyday life depends on multiple factors including, but not limited to, intact physical and mental capacity. In the United States, significant public resources are dedicated to providing assistance to those in need. A key aspect of assistance programs is to provide ongoing assessment of individuals. We used two sources of data in order to inform CADLAC system design, train machine learning models, and to develop a database to support rulebased approaches used by the system. One source of data consisted of a survey that was administered to certified assessors, and the other consisted. Of anonymized historical assessment data shared by the Minnesota Department of Human Services (DHS)

Survey Data
Synthetic Profiles
System Design
Domain Classifier
Intent Classifier
Named Entity Recognizer
Dialogue Manager
Natural Language Generation
Voice Services
ASR Service
Limitations and Future
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call