SLURP: A Spoken Language Understanding Resource Package
SLURP: A Spoken Language Understanding Resource Package
复制标题
DOI：
10.18653/v1/2020.emnlp-main.588
复制
发表时间：
2020-11
期刊：
影响因子：
--
通讯作者：
E. Bastianelli;Andrea Vanzo;P. Swietojanski;Verena Rieser
中科院分区：
文献类型：
--
作者：
E. Bastianelli;Andrea Vanzo;P. Swietojanski;Verena Rieser
口语理解直接从音频数据中推断语义，从而有望减少最终用户应用程序中的错误传播和误解。然而，可公开获得的SLU资源是有限的。在本文中，我们发布了SLURP，一个新的SLU包，包含以下内容：（1）一个新的具有挑战性的英语数据集，跨越18个领域，比现有的数据集更大，语言更多样化;（2）基于最先进的NLU和ASR系统的竞争基线;（3）一个新的透明的实体标签指标，可以进行详细的错误分析，以确定潜在的改进领域。SLURP可在https://github.com/pswietojanski/slurp上获得。
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.