利用多语言自监督预训练模型进行序列到序列的端到端口语语言理解
Leveraging Multilingual Self-Supervised Pretrained Models for Sequence-to-Sequence End-to-End Spoken Language Understanding
AI总结：
本文提出一种整合多语言预训练语音和文本模型的统一方法，以生成方式在四种语言的六个数据集上执行端到端口语语言理解，通过7000小时多语言数据预训练，在多个数据集上超越最先进水平，并在PortMEDIA-Language数据集上显著提升性能。
摘要：
已有多种方法利用预训练模型进行端到端口语语言理解（E2E-SLU），然而其评估往往缺乏多语言设置以及需要预测词汇填充符（如槽填充）的任务。在这项工作中，我们提出了一种统一方法，该方法整合了多语言预训练语音和文本模型，并以生成方式在四种语言的六个数据集上执行E2E-SLU，包括词汇填充符的预测。我们研究了如何通过使用多种训练目标在广泛可用的语音识别数据上进行预训练来改进所提出的方法。在7000小时的多语言数据上进行预训练使我们最终在两个SLU数据集上超越了最先进水平，并在另外两个SLU数据集上部分超越。最后，我们检验了所提出模型的跨语言能力，并在PortMEDIA-Language数据集上将已知最佳结果提高了近一半，实现了23.65%的概念/值错误率。
英文摘要：
A number of methods have been proposed for End-to-End Spoken Language Understanding (E2E-SLU) using pretrained models, however their evaluation often lacks multilingual setup and tasks that require prediction of lexical fillers, such as slot filling. In this work, we propose a unified method that integrates multilingual pretrained speech and text models and performs E2E-SLU on six datasets in four languages in a generative manner, including the prediction of lexical fillers. We investigate how the proposed method can be improved by pretraining on widely available speech recognition data using several training objectives. Pretraining on 7000 hours of multilingual data allows us to outperform the state-of-the-art ultimately on two SLU datasets and partly on two more SLU datasets. Finally, we examine the cross-lingual capabilities of the proposed model and improve on the best known result on the PortMEDIA-Language dataset by almost half, achieving a Concept/Value Error Rate of 23.65%.
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。
