Token-level Sequence Labeling for Spoken Language Understanding using Compositional End-to-End Models

TL;DR

This paper introduces compositional end-to-end spoken language understanding systems that explicitly separate speech recognition from language understanding, improving performance and compatibility with existing models.

Contribution

The authors propose a modular end-to-end SLU framework that integrates intermediate ASR decoders, enabling token-level sequence labeling and better performance.

Findings

Outperforms cascaded and direct end-to-end models on NER tasks

Allows use of pre-trained ASR and NLU components

Enables performance monitoring of individual modules

Abstract

End-to-end spoken language understanding (SLU) systems are gaining popularity over cascaded approaches due to their simplicity and ability to avoid error propagation. However, these systems model sequence labeling as a sequence prediction task causing a divergence from its well-established token-level tagging formulation. We build compositional end-to-end SLU systems that explicitly separate the added complexity of recognizing spoken mentions in SLU from the NLU task of sequence labeling. By relying on intermediate decoders trained for ASR, our end-to-end systems transform the input modality from speech to token-level representations that can be used in the traditional sequence labeling framework. This composition of ASR and NLU formulations in our end-to-end SLU system offers direct compatibility with pre-trained ASR and NLU systems, allows performance monitoring of individual components and enables the use of globally normalized losses like CRF, making them attractive in practical scenarios. Our models outperform both cascaded and direct end-to-end models on a labeling task of named entity recognition across SLU benchmarks.