Personalized Query Rewriting in Conversational AI Agents

TL;DR

This paper introduces a personalized query rewriting method for conversational AI that uses user history to improve understanding and reduce errors, employing neural retrieval and pointer-generator models with hierarchical attention.

Contribution

It presents a novel neural approach utilizing user memory for personalized query rewriting, enhancing error recovery in conversational AI systems.

Findings

Models outperform baselines in query rewriting accuracy

Leveraging user history improves intent recovery

Hierarchical attention enhances model performance

Abstract

Spoken language understanding (SLU) systems in conversational AI agents often experience errors in the form of misrecognitions by automatic speech recognition (ASR) or semantic gaps in natural language understanding (NLU). These errors easily translate to user frustrations, particularly so in recurrent events e.g. regularly toggling an appliance, calling a frequent contact, etc. In this work, we propose a query rewriting approach by leveraging users' historically successful interactions as a form of memory. We present a neural retrieval model and a pointer-generator network with hierarchical attention and show that they perform significantly better at the query rewriting task with the aforementioned user memories than without. We also highlight how our approach with the proposed models leverages the structural and semantic diversity in ASR's output towards recovering users' intents.