Explainable and Accurate Natural Language Understanding for Voice Assistants and Beyond

TL;DR

This paper presents a method to make joint natural language understanding models for voice assistants inherently explainable at granular levels, maintaining high accuracy and extending applicability to other classification tasks like sentiment analysis and NER.

Contribution

The authors develop an inherently explainable joint NLU model that preserves accuracy and can be adapted for other classification tasks, addressing the explainability gap in deep learning models.

Findings

Achieves explainability without sacrificing accuracy

Extends explainability approach to sentiment analysis and NER

Demonstrates improved trustworthiness of NLU models

Abstract

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.