Data Augmentation for Voice-Assistant NLU using BERT-based Interchangeable Rephrase
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.
Author: Akhila Yerukola, Hongxia Jin
Published: European Association for Computational Linguistics (EACL)
Date: Apr 21, 2021