arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2106.15919cs.CLcs.SDeess.AS
收藏

关于口语语言理解接口的联合训练

On joint training with interfaces for spoken language understanding

Amazon Alexa AI(亚马逊Alexa人工智能部门)

Anirudh Raju, Milind Rao, Gautam Tiwari, Pranav Dheram, Bryan Anderson, Zhe Zhang, Chul Lee, Bach Bui, Ariya Rastrow

摘要:

口语语言理解(SLU)系统从输入语音话语中提取与意图和槽相关联的文本转录和语义。SLU系统通常包括(1)自动语音识别(ASR)模块,(2)暴露来自ASR的相关输出的接口模块,以及(3)自然语言理解(NLU)模块。SLU系统中的接口携带关于文本翻译的信息或更丰富的信息,如从ASR到NLU的神经嵌入。在本文中,我们研究接口如何影响口语语言理解的联合训练。最值得注意的是,我们在公开的50小时SLURP数据集上获得了最先进的结果。我们首先利用通过文本接口连接的大型预训练ASR和NLU模型,然后通过序列损失函数联合训练这两个模型。对于不使用预训练模型的场景,通过使用更丰富的神经接口的联合序列丢失训练获得最佳结果。最后,我们展示了利用预训练模型增加训练数据大小的总体影响。

英文摘要:

Spoken language understanding (SLU) systems extract both text transcripts and semantics associated with intents and slots from input speech utterances. SLU systems usually consist of (1) an automatic speech recognition (ASR) module, (2) an interface module that exposes relevant outputs from ASR, and (3) a natural language understanding (NLU) module. Interfaces in SLU systems carry information on text transcriptions or richer information like neural embeddings from ASR to NLU. In this paper, we study how interfaces affect joint-training for spoken language understanding. Most notably, we obtain the state-of-the-art results on the publicly available 50-hr SLURP dataset. We first leverage large-size pretrained ASR and NLU models that are connected by a text interface, and then jointly train both models via a sequence loss function. For scenarios where pretrained models are not utilized, the best results are obtained through a joint sequence loss training using richer neural interfaces. Finally, we show the overall diminishing impact of leveraging pretrained models with increased training data size.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑