Explainable and Accurate Natural Language Understanding for Voice Assistants and Beyond
This addresses the need for user trust in voice assistants and other AI systems by making opaque deep learning models inherently explainable, with potential applications in general classification tasks.
The paper tackles the problem of making joint natural language understanding models both accurate and explainable, achieving comparable accuracy while providing granular explanations without compromising performance.
Joint intent detection and slot filling, which is also termed as joint NLU (Natural Language Understanding) is invaluable for smart voice assistants. Recent advancements in this area have been heavily focusing on improving accuracy using various techniques. Explainability is undoubtedly an important aspect for deep learning-based models including joint NLU models. Without explainability, their decisions are opaque to the outside world and hence, have tendency to lack user trust. Therefore to bridge this gap, we transform the full joint NLU model to be `inherently' explainable at granular levels without compromising on accuracy. Further, as we enable the full joint NLU model explainable, we show that our extension can be successfully used in other general classification tasks. We demonstrate this using sentiment analysis and named entity recognition.