Jointly Encoding Word Confusion Network and Dialogue Context with BERT for Spoken Language Understanding

TL;DR

This paper introduces a BERT-based model that jointly encodes word confusion networks and dialogue context to improve spoken language understanding, significantly reducing errors caused by ASR inaccuracies.

Contribution

It presents a novel WCN-BERT SLU model that effectively combines WCNs and dialogue context within BERT, outperforming previous SLU methods on benchmark datasets.

Findings

Outperforms previous state-of-the-art models on DSTC2 benchmark.

Effectively encodes ASR uncertainties and dialogue context.

Significant improvement in SLU accuracy with the proposed method.

Abstract

Spoken Language Understanding (SLU) converts hypotheses from automatic speech recognizer (ASR) into structured semantic representations. ASR recognition errors can severely degenerate the performance of the subsequent SLU module. To address this issue, word confusion networks (WCNs) have been used to encode the input for SLU, which contain richer information than 1-best or n-best hypotheses list. To further eliminate ambiguity, the last system act of dialogue context is also utilized as additional input. In this paper, a novel BERT based SLU model (WCN-BERT SLU) is proposed to encode WCNs and the dialogue context jointly. It can integrate both structural information and ASR posterior probabilities of WCNs in the BERT architecture. Experiments on DSTC2, a benchmark of SLU, show that the proposed method is effective and can outperform previous state-of-the-art models significantly.