This paper describes our system for the low-resource domain adaptation track (Track 3) in Spoken Language Understanding Grand Challenge, which is a part of ICASSP Signal Processing Grand Challenge 2023. In the track, we adopt a pipeline approach of ASR and NLU. For ASR, we fine-tune Whisper for each domain with upsampling. For NLU, we fine-tune BART on all the Track3 data and then on low-resource domain data. We apply masked LM (MLM) -based data augmentation, where some of input tokens and corresponding target labels are replaced using MLM. We also apply a retrieval-based approach, where model input is augmented with similar training samples. As a result, we achieved exact match (EM) accuracy 63.3/75.0 (average: 69.15) for reminder/weather domain, and won the 1st place at the challenge.

翻译：本文描述了我们在口语理解大挑战赛（ICASSP信号处理大挑战赛2023的一部分）低资源领域自适应赛道（Track 3）中所提出的系统方案。在该赛道中，我们采用ASR与NLU的流水线方法。对于ASR，我们通过上采样技术对Whisper模型进行各领域的微调。对于NLU，我们首先在全部Track 3数据上微调BART模型，再针对低资源领域数据继续微调。我们应用基于掩码语言模型（MLM）的数据增强方法，通过MLM替换部分输入词元及对应目标标签。同时采用基于检索的方法，将相似训练样本增广至模型输入。最终，我们在提醒/天气领域实现了63.3/75.0（平均：69.15）的精确匹配（EM）准确率，并荣获该挑战赛第一名。