Gaining Insights into Unrecognized User Utterances in Task-Oriented Dialog Systems
This work addresses the challenge of improving intent identification accuracy for developers of commercial task-oriented dialog systems, but it appears incremental as it builds on existing clustering and analysis methods.
The paper tackles the problem of analyzing unrecognized user utterances in task-oriented dialog systems by presenting an end-to-end pipeline with a tailored clustering algorithm, novel cluster representative extraction, and cluster naming, deployed in a commercial system and evaluated to show benefits.
The rapidly growing market demand for automatic dialogue agents capable of goal-oriented behavior has caused many tech-industry leaders to invest considerable efforts into task-oriented dialog systems. The success of these systems is highly dependent on the accuracy of their intent identification -- the process of deducing the goal or meaning of the user's request and mapping it to one of the known intents for further processing. Gaining insights into unrecognized utterances -- user requests the systems fail to attribute to a known intent -- is therefore a key process in continuous improvement of goal-oriented dialog systems. We present an end-to-end pipeline for processing unrecognized user utterances, deployed in a real-world, commercial task-oriented dialog system, including a specifically-tailored clustering algorithm, a novel approach to cluster representative extraction, and cluster naming. We evaluated the proposed components, demonstrating their benefits in the analysis of unrecognized user requests.