{
 "id": "mteb/StatcanDialogueDatasetRetrieval",
 "owner": "mteb",
 "name": "StatcanDialogueDatasetRetrieval",
 "downloads": 1334,
 "likes": 0,
 "last_modified": "2025-06-19T19:47:55.000Z",
 "stated_licence": "other",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [
  {
   "id": "McGill-NLP/statcan-dialogue-dataset-retrieval",
   "licence": null,
   "found": true,
   "evidence": "https://huggingface.co/datasets/McGill-NLP/statcan-dialogue-dataset-retrieval/blob/7a26938c93e99e0759a1df416896bb72527e2f33/README.md"
  }
 ],
 "gated": false,
 "tasks": [
  "text-retrieval"
 ],
 "citation": "@inproceedings{lu-etal-2023-statcan,\n  address = {Dubrovnik, Croatia},\n  author = {Lu, Xing Han  and\nReddy, Siva  and\nde Vries, Harm},\n  booktitle = {Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics},\n  month = may,\n  pages = {2799--2829},\n  publisher = {Association for Computational Linguistics},\n  title = {The {S}tat{C}an Dialogue Dataset: Retrieving Data Tables through Conversations with Genuine Intents},\n  url = {https://arxiv.org/abs/2304.01412},\n  year = {2023},\n}\n\n\n@article{enevoldsen2025mmtebmassivemultilingualtext,\n  title={MMTEB: Massive Multilingual Text Embedding Benchmark},\n  author={Kenneth Enevoldsen and Isaac Chung and Imene Kerboua and Márton Kardos and Ashwin Mathur and David Stap and Jay Gala and Wissam Siblini and Dominik Krzemiński and Genta Indra Winata and Saba Sturua and Saiteja Utpala and Mathieu Ciancone and Marion Schaeffer and Gabriel Sequeira and Diganta Misra and Shreeya Dhakal and Jonathan Rystrøm and Roman Solomatin and Ömer Çağatan and Akash Kundu and Martin Bernstorff and Shitao Xiao and Akshita Sukhlecha and Bhavish Pahwa and Rafał Poświata and Kranthi Kiran GV and Shawon Ashraf and Daniel Auras and Björn Plüster and Jan Philipp Harries and Loïc Magne and Isabelle Mohr and Mariya Hendriksen and Dawei Zhu and Hippolyte Gisserot-Boukhlef and Tom Aarsen and Jan Kostkan and Konrad Wojtasik and Taemin Lee and Marek Šuppa and Crystina Zhang and Roberta Rocca and Mohammed Hamdy and Andriano",
 "signal": "unclear",
 "reason": "The checks could not identify a recognised licence ID in the dataset's metadata.",
 "revision": "6f9747b22a93c6cf714945bca43576089fb80de3",
 "stated_evidence": "https://huggingface.co/datasets/mteb/StatcanDialogueDatasetRetrieval/blob/6f9747b22a93c6cf714945bca43576089fb80de3/README.md",
 "file_evidence": "https://huggingface.co/datasets/mteb/StatcanDialogueDatasetRetrieval/tree/6f9747b22a93c6cf714945bca43576089fb80de3",
 "card_nc": false
}