Personalized Query Rewriting in Conversational AI Agents
This addresses user frustrations in recurrent tasks like toggling appliances or calling contacts, but it is incremental as it builds on existing query rewriting methods.
The paper tackles errors in conversational AI agents from speech recognition and understanding by using users' past successful interactions as memory to rewrite queries, achieving significant performance improvements with neural retrieval and pointer-generator models.
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.