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

arXiv: https://arxiv.org/abs/2005.11640 · HTML: https://mlsanity.com/paper/2005.11640/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 May 2020.

## Built on by (most cited first, 8 of 8)

- [Phoneme-BERT: Joint Language Modelling of Phoneme Sequence and ASR Transcript](https://mlsanity.com/paper/2102.00804/) (2021)
- [N-Best ASR Transformer: Enhancing SLU Performance using Multiple ASR Hypotheses](https://mlsanity.com/paper/2106.06519/) (2021)
- [Towards ASR Robust Spoken Language Understanding Through In-Context Learning With Word Confusion Networks](https://mlsanity.com/paper/2401.02921/) (2024)
- [ASR-Generated Text for Language Model Pre-training Applied to Speech Tasks](https://mlsanity.com/paper/2207.01893/) (2022)
- [End-to-End Spoken Language Understanding: Performance analyses of a voice command task in a low resource setting](https://mlsanity.com/paper/2207.08179/) (2022)
- [Effectiveness of Text, Acoustic, and Lattice-based representations in Spoken Language Understanding tasks](https://mlsanity.com/paper/2212.08489/) (2022)
- [Robust Unstructured Knowledge Access in Conversational Dialogue with ASR Errors](https://mlsanity.com/paper/2211.03990/) (2022)
- [Meta Auxiliary Learning for Low-resource Spoken Language Understanding](https://mlsanity.com/paper/2206.12774/) (2022)

## Abstract (arXiv)

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.