OneNet: Joint Domain, Intent, Slot Prediction for Spoken Language Understanding

TL;DR

This paper introduces OneNet, a unified neural network model that jointly predicts domain, intent, and slots in spoken language understanding, reducing errors and improving performance over traditional pipeline systems.

Contribution

The paper presents a novel multitask learning architecture that integrates domain, intent, and slot prediction into a single model, enhancing accuracy on real user data.

Findings

Significant improvements in all three tasks over strong baselines

Effective use of orthography-sensitive encoding and curriculum training

Outperforms models with oracle domain prediction

Abstract

In practice, most spoken language understanding systems process user input in a pipelined manner; first domain is predicted, then intent and semantic slots are inferred according to the semantic frames of the predicted domain. The pipeline approach, however, has some disadvantages: error propagation and lack of information sharing. To address these issues, we present a unified neural network that jointly performs domain, intent, and slot predictions. Our approach adopts a principled architecture for multitask learning to fold in the state-of-the-art models for each task. With a few more ingredients, e.g. orthography-sensitive input encoding and curriculum training, our model delivered significant improvements in all three tasks across all domains over strong baselines, including one using oracle prediction for domain detection, on real user data of a commercial personal assistant.