Data Augmentation for Voice-Assistant NLU using BERT-based Interchangeable Rephrase
Not on the map. Why?
Abstract (arXiv)
We introduce a data augmentation technique based on byte pair encoding and a BERT-like self-attention model to boost performance on spoken language understanding tasks. We compare and evaluate this method with a range of augmentation techniques encompassing generative models such as VAEs and performance-boosting techniques such as synonym replacement and back-translation. We show our method performs strongly on domain and intent classification tasks for a voice assistant and in a user-study focused on utterance naturalness and semantic similarity.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 12 of its 21 references that are in the map. First posted on arXiv 16 Apr 2021.
Builds on
12 of 21 references.
References · 12
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
- 2019DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lightercited by 4,243
- 2015Neural Machine Translation of Rare Words with Subword Unitscited by 2,898
- 2019EDA: Easy Data Augmentation Techniques for Boosting Performance on Text Classification Taskscited by 800
- 2015Generating Sentences from a Continuous Spacecited by 607
- 2015Skip-Thought Vectorscited by 321
- 2017Toward Controlled Generation of Textcited by 271
- 2018QANet: Combining Local Convolution with Global Self-Attention for Reading Comprehensioncited by 164
- 2017Controlling Linguistic Style Aspects in Neural Language Generationcited by 147
- 2019Do Massively Pretrained Language Models Make Better Storytellers?cited by 90
- 2017Generating Sentences by Editing Prototypescited by 88
- 2018Unsupervised Natural Language Generation with Denoising Autoencoderscited by 9
Built on by
Citing papers per year: 2023: 1; 2024: 1.
2 papers.