Data Augmentation With Atomic Templates For Spoken Language Understanding

Abstract

Spoken Language Understanding (SLU) converts user utterances into structured semantic representations. Data sparsity is one of the main obstacles of SLU due to the high cost of human annotation, especially when domain changes or a new domain comes. In this work, we propose a data augmentation method with atomic templates for SLU, which involves minimum human efforts. The atomic templates produce exemplars for fine-grained constituents of semantic representations. We propose an encoder-decoder model to generate the whole utterance from atomic exemplars. Moreover, the generator could be transferred from source domains to help a new domain which has little data. Experimental results show that our method achieves significant improvements on DSTC 2\&3 dataset which is a domain adaptation setting of SLU.

Stats

• citations4
• S2 citations—
• github stars0
• HF likes0
• heat score5.24
• arxiv keyzhao2019data

Related papers

• Data Augmentation For Spoken Language Understanding Via Pretrained Language Models (2020)0.00
• Data Augmentation For Spoken Language Understanding Via Joint Variational Generation (2018)10.61
• Towards Reducing The Need For Speech Training Data To Build Spoken Language Understanding Systems (2022)8.35
• Bridging The Gap Between Clean Data Training And Real-world Inference For Spoken Language Understanding (2021)0.00
• Learning From Multiple Noisy Augmented Data Sets For Better Cross-lingual Spoken Language Understanding (2021)3.58
• Large-scale Transfer Learning For Low-resource Spoken Language Understanding (2020)2.26
• AFD-SLU: Adaptive Feature Distillation For Spoken Language Understanding (2025)0.00
• Unislu: Unified Spoken Language Understanding From Heterogeneous Cross-task Datasets (2025)0.00