论文标题
Slurp：一种口语理解资源包
SLURP: A Spoken Language Understanding Resource Package
论文作者
论文摘要
口语理解直接从音频数据中注入语义含义，因此有望减少最终用户应用程序中的错误传播和误解。但是，公开可用的SLU资源是有限的。在本文中，我们发布了一个新的SLURP，这是一种新的SLU软件包，其中包含以下内容：（1）英文中的一个新的具有挑战性的数据集，该数据集跨越了18个域，该数据集比现有数据集更大，语言上更加多样化； （2）基于最先进的NLU和ASR系统的竞争基准； （3）实体标签的新透明指标，可实现详细的错误分析，以识别潜在的改进领域。 Slurp可从https：//github.com/pswietojanski/slurp获得。
Spoken Language Understanding infers semantic meaning directly from audio data, and thus promises to reduce error propagation and misunderstandings in end-user applications. However, publicly available SLU resources are limited. In this paper, we release SLURP, a new SLU package containing the following: (1) A new challenging dataset in English spanning 18 domains, which is substantially bigger and linguistically more diverse than existing datasets; (2) Competitive baselines based on state-of-the-art NLU and ASR systems; (3) A new transparent metric for entity labelling which enables a detailed error analysis for identifying potential areas of improvement. SLURP is available at https: //github.com/pswietojanski/slurp.
