Data Augmentation for Voice-Assistant NLU using BERT-based Interchangeable Rephrase
Akhila Yerukola, Mason Bretan, Hongxia Jin
Speech Short paper Paper
You can open the pre-recorded video in separate windows.
Abstract:
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.
NOTE: Video may display a random order of authors.
Correct author list is at the top of this page.