SLURP: A Spoken Language Understanding Resource Package
By Emanuele Bastianelli, Andrea Vanzo, Pawel Swietojanski, Verena Rieser. Conference on Empirical Methods in Natural Language Processing, 2020
303 citations recorded by the source corpus.
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.
Subfields: Artificial Intelligence
View Paper: https://www.semanticscholar.org/paper/11aba1be0ccdbe291fc4e469e458b832d5228203
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Yoshua Bengio
- Gabriel Synnaeve
- Yossi Adi
- Mohit Bansal
- Alexis Conneau
- Wei-Ning Hsu
- Jianfeng Gao
- Yonatan Belinkov
Citations in the corpus
- MASSIVE: A 1M-Example Multilingual Natural Language Understanding Dataset with 51 Typologically-Diverse Languages (2022, methodology): “The authors updated the dataset and added audio and ASR transcriptions in the release of the Spoken Language Understanding Resource Package (SLURP) (Bastianelli et al., 2020), allowing for full end-to-end Spoken Language Understanding (SLU) evaluation similar to the Fluent Speech Commands dataset (L”
- LauraGPT: Listen, Attend, Understand, and Regenerate Audio with GPT (2023, methodology): “For the SLU task, we use the multi-domain Spoken Language Understanding Resource Package (SLURP) dataset (Bastianelli et al., 2020), which covers 18 scenarios.”
- SpeechBrain: A General-Purpose Speech Toolkit (2021, methodology): “Our direct recipe using a wav2vec 2.0 encoder outperforms the HerMiT baseline provided in the original SLURP paper [53] across all metrics.”
- Textually Pretrained Speech Language Models (2023, background): “Although it contains more than just textual content (e.g., intonation, non-verbal vocalizations), most spoken language understanding systems are limited to its textual form [Wen et al., 2015, Bastianelli et al., 2020, Gupta, 2022]; see Qin et al. [2021] for a recent survey.”