Data Augmentation with Atomic Templates for Spoken Language Understanding
This addresses data scarcity for SLU systems, especially in new domains, though it appears incremental as it builds on existing template-based augmentation approaches.
The paper tackles data sparsity in Spoken Language Understanding (SLU) by proposing a data augmentation method using atomic templates to generate utterances with minimal human effort, achieving significant improvements on the DSTC 2&3 dataset in domain adaptation settings.
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.