Handling Long-Tail Queries with Slice-Aware Conversational Systems

TL;DR

This paper introduces a slice-aware learning approach to enhance conversational AI systems by focusing on improving performance on low-frequency tail queries without sacrificing overall accuracy.

Contribution

The paper proposes a novel slice-aware architecture and weak supervision labeling functions to specifically target and improve tail intent performance in conversational AI systems.

Findings

Improved tail intent accuracy in live traffic data

Maintained overall system performance

Demonstrated effectiveness of slice-aware learning in real-world scenarios

Abstract

We have been witnessing the usefulness of conversational AI systems such as Siri and Alexa, directly impacting our daily lives. These systems normally rely on machine learning models evolving over time to provide quality user experience. However, the development and improvement of the models are challenging because they need to support both high (head) and low (tail) usage scenarios, requiring fine-grained modeling strategies for specific data subsets or slices. In this paper, we explore the recent concept of slice-based learning (SBL) (Chen et al., 2019) to improve our baseline conversational skill routing system on the tail yet critical query traffic. We first define a set of labeling functions to generate weak supervision data for the tail intents. We then extend the baseline model towards a slice-aware architecture, which monitors and improves the model performance on the selected tail intents. Applied to de-identified live traffic from a commercial conversational AI system, our experiments show that the slice-aware model is beneficial in improving model performance for the tail intents while maintaining the overall performance.