Automatically Training a Problematic Dialogue Predictor for a Spoken Dialogue System

TL;DR

This paper presents a method for automatically training a predictor to identify problematic dialogues in spoken systems, improving early detection and response to issues to enhance user experience.

Contribution

It introduces an automatic training approach for a Problematic Dialogue Predictor that uses early dialogue features to improve prediction accuracy in spoken dialogue systems.

Findings

Predictor improves accuracy by 13.2% over baseline.

Features from initial exchanges are effective for early problem detection.

The predictor can inform system decisions to transfer or repair dialogues.

Abstract

Spoken dialogue systems promise efficient and natural access to a large variety of information sources and services from any phone. However, current spoken dialogue systems are deficient in their strategies for preventing, identifying and repairing problems that arise in the conversation. This paper reports results on automatically training a Problematic Dialogue Predictor to predict problematic human-computer dialogues using a corpus of 4692 dialogues collected with the 'How May I Help You' (SM) spoken dialogue system. The Problematic Dialogue Predictor can be immediately applied to the system's decision of whether to transfer the call to a human customer care agent, or be used as a cue to the system's dialogue manager to modify its behavior to repair problems, and even perhaps, to prevent them. We show that a Problematic Dialogue Predictor using automatically-obtainable features from the first two exchanges in the dialogue can predict problematic dialogues 13.2% more accurately than the baseline.