Data Augmentation with Atomic Templates for Spoken Language Understanding

By Zijian Zhao, Su Zhu, Kai Yu. 2019

29 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Management Science and Operations Research, Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Mohit Bansal
2. Jonathan Berant
3. Eduard H. Hovy
4. Luke S. Zettlemoyer
5. Alon Talmor
6. Percy Liang
7. Yejin Choi
8. Jason Wei

In Management Science and Operations Research

1. Bowen Tan
2. Sarath Chandar
3. Alon Talmor
4. Lu Chen
5. Su Zhu
6. Eduard H. Hovy
7. Silin Gao
8. Steven Y. Feng

In Natural Language Processing

1. Jonathan Berant
2. Alon Talmor
3. Eduard H. Hovy
4. Mohit Bansal
5. Jason Wei
6. Varun Prashant Gangal
7. Teruko Mitamura
8. Soroush Vosoughi

Citations in the corpus

• A Survey of Data Augmentation Approaches for NLP (2021, background): “Hou et al. (2018), Kim et al. (2019), Zhao et al. (2019), and Yoo et al. (2019) investigate DA methods for dialogue and spoken language understanding (SLU), including generative latent variable models.”
• Turning Tables: Generating Examples from Semi-structured Tables for Endowing Language Models with Reasoning Skills (2021, background): “, 2020), and to improve consistency (Asai and Hajishirzi, 2020), and zero-shot accuracy (Zhao et al., 2019).”
• Paraphrase Augmented Task-Oriented Dialog Generation (2020, background): “Such an idea led to recent augmentation work on the language understanding task (Hou et al., 2018; Kim et al., 2019; Yoo et al., 2019; Zhao et al., 2019).”
• Schema-Guided Multi-Domain Dialogue State Tracking with Graph Attention Neural Networks (2020, methodology): “To overcome the data sparsity problem, we would like to try data augmentation methods (Zhao, Zhu, and Yu 2019a; Cao et al. 2019).”
• A Closer Look At Feature Space Data Augmentation For Few-Shot Intent Classification (2019, background): “For text classification, several text generation based data augmentation techniques have also been explored (Hou et al., 2018; Zhao et al., 2019; Guu et al., 2018; Yoo et al., 2018; Cho et al., 2019a).”
• Data Augmentation Approaches in Natural Language Processing: A Survey (2021, unknown): “Model Generation [18], [69], [105], [106], [107] [18], [108], [109], [110] [18], [16], [68], [17], [111], [76]”