SLURP: A Spoken Language Understanding Resource Package

This resource contains supplementary audio material used in our EMNLP 2020 paper where 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. Textual annotations are released via the corresponding Github repository (for ease of maintenance).