{
 "id": "unimelb-nlp/wikiann",
 "owner": "unimelb-nlp",
 "name": "wikiann",
 "downloads": 27525,
 "likes": 126,
 "last_modified": "2024-02-22T14:32:02.000Z",
 "stated_licence": "unknown",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "token-classification"
 ],
 "citation": "@inproceedings{pan-etal-2017-cross,\n    title = \"Cross-lingual Name Tagging and Linking for 282 Languages\",\n    author = \"Pan, Xiaoman  and\n      Zhang, Boliang  and\n      May, Jonathan  and\n      Nothman, Joel  and\n      Knight, Kevin  and\n      Ji, Heng\",\n    booktitle = \"Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)\",\n    month = jul,\n    year = \"2017\",\n    address = \"Vancouver, Canada\",\n    publisher = \"Association for Computational Linguistics\",\n    url = \"https://www.aclweb.org/anthology/P17-1178\",\n    doi = \"10.18653/v1/P17-1178\",\n    pages = \"1946--1958\",\n    abstract = \"The ambitious goal of this work is to develop a cross-lingual name tagging and linking framework for 282 languages that exist in Wikipedia. Given a document in any of these languages, our framework is able to identify name mentions, assign a coarse-grained or fine-grained type to each mention, and link it to an English Knowledge Base (KB) if it is linkable. We achieve this goal by performing a series of new KB mining methods: generating {``}silver-standard{''} annotations by transferring annotations from English to other languages through cross-lingual links and KB properties, refining annotations through self-training and topic selection, deriving language-specific morphology features from anchor links, and mining word translation pairs from cross-lingual links. Both name tagging and linking results for 282 languages are promising on W",
 "signal": "unclear",
 "reason": "The checks could not identify a recognised licence ID in the dataset's metadata."
}