Acid-nlu aggregates pre-existing datasets from other sources. See below for information about the original sources including links to repositories, associated papers, citation information, and licenses.
home: https://github.com/codycollier/acid-nlu
- repo: https://github.com/clinc/oos-eval
- paper: https://arxiv.org/abs/1909.02027
- paper: https://www.aclweb.org/anthology/D19-1131/
- license: CC BY 3.0 (Creative Commons Attribution 3.0 Unported)
- citation:
@inproceedings{larson-etal-2019-evaluation,
title = "An Evaluation Dataset for Intent Classification and Out-of-Scope Prediction",
author = "Larson, Stefan and
Mahendran, Anish and
Peper, Joseph J. and
Clarke, Christopher and
Lee, Andrew and
Hill, Parker and
Kummerfeld, Jonathan K. and
Leach, Kevin and
Laurenzano, Michael A. and
Tang, Lingjia and
Mars, Jason",
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)",
year = "2019",
url = "https://www.aclweb.org/anthology/D19-1131"
}
- repo: https://github.com/PolyAI-LDN/task-specific-datasets
- paper: https://arxiv.org/abs/2003.04807
- license: CC BY-NC 4.0 (Attribution-NonCommercial 4.0 International)
- citation:
@inproceedings{Casanueva2020,
author = {I{\~{n}}igo Casanueva and Tadas Temcinas and Daniela Gerz and Matthew Henderson and Ivan Vulic},
title = {Efficient Intent Detection with Dual Sentence Encoders},
year = {2020},
month = {mar},
note = {Data available at https://github.com/PolyAI-LDN/task-specific-datasets},
url = {https://arxiv.org/abs/2003.04807},
booktitle = {Arxiv},
}
- repo: https://github.com/sebischair/NLU-Evaluation-Corpora
- paper: https://www.sigdial.org/files/workshops/conference18/proceedings/pdf/SIGDIAL22.pdf
- alias: ask ubuntu corpus, chatbot corpus, web applications corpus
- license: CC BY-SA 3.0 (Creative Commons Attribution-ShareAlike 3.0 Unported)
- citation:
@InProceedings{braun-EtAl:2017:SIGDIAL,
author = {Braun, Daniel and Hernandez-Mendez, Adrian and Matthes, Florian and Langen, Manfred},
title = {Evaluating Natural Language Understanding Services for Conversational Question Answering Systems},
booktitle = {Proceedings of the 18th Annual SIGdial Meeting on Discourse and Dialogue},
month = {August},
year = {2017},
address = {Saarbrücken, Germany},
publisher = {Association for Computational Linguistics},
pages = {174--185},
url = {http://www.aclweb.org/anthology/W17-3622}
}
- repo: https://github.com/snipsco/nlu-benchmark
- paper: https://arxiv.org/abs/1805.10190
- license: CC0-1.0 (Creative Commons Zero v1.0 Universal)
- citation:
@misc{coucke2018snips,
title={Snips Voice Platform: an embedded Spoken Language Understanding system for private-by-design voice interfaces},
author={Alice Coucke and Alaa Saade and Adrien Ball and Théodore Bluche and Alexandre Caulier and David Leroy and Clément Doumouro and Thibault Gisselbrecht and Francesco Caltagirone and Thibaut Lavril and Maël Primet and Joseph Dureau},
year={2018},
eprint={1805.10190},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
- repo: https://github.com/xliuhw/NLU-Evaluation-Data
- paper: https://arxiv.org/abs/1903.05566
- paper: https://iwsds2019.unikore.it/program/
- alias: hwu64
- license: CC BY-SA 3.0 (Creative Commons Attribution-ShareAlike 3.0 Unported)
- citation:
@InProceedings{XLiu.etal:IWSDS2019,
author = {Xingkun Liu, Arash Eshghi, Pawel Swietojanski and Verena Rieser},
title = {Benchmarking Natural Language Understanding Services for building Conversational Agents},
booktitle = {Proceedings of the Tenth International Workshop on Spoken Dialogue Systems Technology (IWSDS)},
month = {April},
year = {2019},
address = {Ortigia, Siracusa (SR), Italy},
publisher = {Springer},
pages = {xxx--xxx},
url = {http://www.xx.xx/xx/}
}