Joint Online Spoken Language Understanding and Language Modeling with Recurrent Neural Networks

TL;DR

This paper presents a recurrent neural network that jointly performs intent detection, slot filling, and language modeling in spoken language understanding, improving accuracy and robustness in dialogue systems.

Contribution

It introduces a joint RNN model that updates intent estimation online and integrates language modeling with SLU tasks, a novel approach in the field.

Findings

11.8% reduction in language model perplexity

22.3% improvement in intent detection error rate

Effective performance in noisy speech scenarios

Abstract

Speaker intent detection and semantic slot filling are two critical tasks in spoken language understanding (SLU) for dialogue systems. In this paper, we describe a recurrent neural network (RNN) model that jointly performs intent detection, slot filling, and language modeling. The neural network model keeps updating the intent estimation as word in the transcribed utterance arrives and uses it as contextual features in the joint model. Evaluation of the language model and online SLU model is made on the ATIS benchmarking data set. On language modeling task, our joint model achieves 11.8% relative reduction on perplexity comparing to the independent training language model. On SLU tasks, our joint model outperforms the independent task training model by 22.3% on intent detection error rate, with slight degradation on slot filling F1 score. The joint model also shows advantageous performance in the realistic ASR settings with noisy speech input.