Actionable Conversational Quality Indicators for Improving Task-Oriented Dialog Systems

TL;DR

This paper introduces Actionable Conversational Quality Indicators (ACQIs) to identify and improve dialog system responses, demonstrating their effectiveness on real-world and public datasets, and providing a predictive model for practical application.

Contribution

It proposes ACQIs as a novel approach to diagnose and enhance task-oriented dialog systems, combining quality scoring and error categorization.

Findings

Achieved 79% F1-score in predicting ACQIs from message embeddings.

Identified key ACQIs that significantly impact dialog quality.

Predicted potential reduction of 81% in improvement actions needed.

Abstract

Automatic dialog systems have become a mainstream part of online customer service. Many such systems are built, maintained, and improved by customer service specialists, rather than dialog systems engineers and computer programmers. As conversations between people and machines become commonplace, it is critical to understand what is working, what is not, and what actions can be taken to reduce the frequency of inappropriate system responses. These analyses and recommendations need to be presented in terms that directly reflect the user experience rather than the internal dialog processing. This paper introduces and explains the use of Actionable Conversational Quality Indicators (ACQIs), which are used both to recognize parts of dialogs that can be improved, and to recommend how to improve them. This combines benefits of previous approaches, some of which have focused on producing dialog quality scoring while others have sought to categorize the types of errors the dialog system is making. We demonstrate the effectiveness of using ACQIs on LivePerson internal dialog systems used in commercial customer service applications, and on the publicly available CMU LEGOv2 conversational dataset (Raux et al. 2005). We report on the annotation and analysis of conversational datasets showing which ACQIs are important to fix in various situations. The annotated datasets are then used to build a predictive model which uses a turn-based vector embedding of the message texts and achieves an 79% weighted average f1-measure at the task of finding the correct ACQI for a given conversation. We predict that if such a model worked perfectly, the range of potential improvement actions a bot-builder must consider at each turn could be reduced by an average of 81%.