The goal of spoken language understanding (SLU) systems is to determine the
meaning of the input speech signal, unlike speech recognition which aims to
produce verbatim transcripts. Advances in end-to-end (E2E) speech modeling have
made it possible to train solely on semantic entities, which are far cheaper to
collect than verbatim transcripts. We focus on this set prediction problem,
where entity order is unspecified. Using two classes of E2E models, RNN
transducers and attention based encoder-decoders, we show that these models
work best when the training entity sequence is arranged in spoken order. To
improve E2E SLU models when entity spoken order is unknown, we propose a novel
data augmentation technique along with an implicit attention based alignment
method to infer the spoken order. F1 scores significantly increased by more
than 11% for RNN-T and about 2% for attention based encoder-decoder SLU models,
outperforming previously reported results.

本文介绍了利用两类 E2E 模型（RNN 转录器和基于注意力的编码器 - 解码器）进行口语语言理解系统的语义实体预测的研究，以及提出的一种数据增强技术和一种隐式注意力对齐方法来推断口语顺序，从而提高 E2E SLU 模型的性能。相较于以前报导的结果，F1 分数显著提高了超过 11％（对于 RNN-T）和约 2％（对于基于注意力的编码器 - 解码器）。