A scalable framework for learning from implicit user feedback to improve natural language understanding in large-scale conversational AI systems
This work addresses the challenge of enhancing NLU performance for conversational AI systems at scale, though it appears incremental as it builds on existing methods for data curation.
The authors tackled the problem of improving Natural Language Understanding (NLU) in large-scale conversational AI systems by leveraging implicit user feedback from production traffic, resulting in demonstrated improvements across 10 domains.
Natural Language Understanding (NLU) is an established component within a conversational AI or digital assistant system, and it is responsible for producing semantic understanding of a user request. We propose a scalable and automatic approach for improving NLU in a large-scale conversational AI system by leveraging implicit user feedback, with an insight that user interaction data and dialog context have rich information embedded from which user satisfaction and intention can be inferred. In particular, we propose a general domain-agnostic framework for curating new supervision data for improving NLU from live production traffic. With an extensive set of experiments, we show the results of applying the framework and improving NLU for a large-scale production system and show its impact across 10 domains.