Attentive Contextual Carryover for Multi-Turn End-to-End Spoken Language Understanding

TL;DR

This paper introduces a multi-turn contextual E2E SLU model using multi-head attention over dialogue history, significantly reducing error rates in spoken language understanding tasks.

Contribution

It proposes a novel attention-based architecture that effectively incorporates dialogue context into end-to-end SLU models, enhancing multi-turn understanding performance.

Findings

Reduces word error rate by 10.8% on a large dataset.

Decreases semantic error rate by 12.6%.

Improves performance over noncontextual baselines.

Abstract

Recent years have seen significant advances in end-to-end (E2E) spoken language understanding (SLU) systems, which directly predict intents and slots from spoken audio. While dialogue history has been exploited to improve conventional text-based natural language understanding systems, current E2E SLU approaches have not yet incorporated such critical contextual signals in multi-turn and task-oriented dialogues. In this work, we propose a contextual E2E SLU model architecture that uses a multi-head attention mechanism over encoded previous utterances and dialogue acts (actions taken by the voice assistant) of a multi-turn dialogue. We detail alternative methods to integrate these contexts into the state-ofthe-art recurrent and transformer-based models. When applied to a large de-identified dataset of utterances collected by a voice assistant, our method reduces average word and semantic error rates by 10.8% and 12.6%, respectively. We also present results on a publicly available dataset and show that our method significantly improves performance over a noncontextual baseline