{
 "id": "mteb/mtop_domain",
 "owner": "mteb",
 "name": "mtop_domain",
 "downloads": 1460,
 "likes": 2,
 "last_modified": "2025-07-19T20:09:24.000Z",
 "stated_licence": "unknown",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "text-classification"
 ],
 "citation": "@inproceedings{li-etal-2021-mtop,\n  abstract = {Scaling semantic parsing models for task-oriented dialog systems to new languages is often expensive and time-consuming due to the lack of available datasets. Available datasets suffer from several shortcomings: a) they contain few languages b) they contain small amounts of labeled examples per language c) they are based on the simple intent and slot detection paradigm for non-compositional queries. In this paper, we present a new multilingual dataset, called MTOP, comprising of 100k annotated utterances in 6 languages across 11 domains. We use this dataset and other publicly available datasets to conduct a comprehensive benchmarking study on using various state-of-the-art multilingual pre-trained models for task-oriented semantic parsing. We achieve an average improvement of +6.3 points on Slot F1 for the two existing multilingual datasets, over best results reported in their experiments. Furthermore, we demonstrate strong zero-shot performance using pre-trained models combined with automatic translation and alignment, and a proposed distant supervision method to reduce the noise in slot label projection.},\n  address = {Online},\n  author = {Li, Haoran  and\nArora, Abhinav  and\nChen, Shuohui  and\nGupta, Anchit  and\nGupta, Sonal  and\nMehdad, Yashar},\n  booktitle = {Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume},\n  doi = {10.18653/v1/2021.eacl-main.257},\n  e",
 "signal": "unclear",
 "reason": "The checks could not identify a recognised licence ID in the dataset's metadata.",
 "revision": "b8451f34e224fe9b3b82ac712dba88dcdc9eb58f",
 "stated_evidence": "https://huggingface.co/datasets/mteb/mtop_domain/blob/b8451f34e224fe9b3b82ac712dba88dcdc9eb58f/README.md",
 "file_evidence": "https://huggingface.co/datasets/mteb/mtop_domain/tree/b8451f34e224fe9b3b82ac712dba88dcdc9eb58f",
 "card_nc": false
}