{
 "id": "ruanchaves/stan_large",
 "owner": "ruanchaves",
 "name": "stan_large",
 "downloads": 80,
 "likes": 0,
 "last_modified": "2022-10-20T19:13:15.000Z",
 "stated_licence": "agpl-3.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "structure-prediction"
 ],
 "citation": "@inproceedings{maddela-etal-2019-multi,\n    title = \"Multi-task Pairwise Neural Ranking for Hashtag Segmentation\",\n    author = \"Maddela, Mounica  and\n      Xu, Wei  and\n      Preo{\\c{t}}iuc-Pietro, Daniel\",\n    booktitle = \"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics\",\n    month = jul,\n    year = \"2019\",\n    address = \"Florence, Italy\",\n    publisher = \"Association for Computational Linguistics\",\n    url = \"https://aclanthology.org/P19-1242\",\n    doi = \"10.18653/v1/P19-1242\",\n    pages = \"2538--2549\",\n    abstract = \"Hashtags are often employed on social media and beyond to add metadata to a textual utterance with the goal of increasing discoverability, aiding search, or providing additional semantics. However, the semantic content of hashtags is not straightforward to infer as these represent ad-hoc conventions which frequently include multiple words joined together and can include abbreviations and unorthodox spellings. We build a dataset of 12,594 hashtags split into individual segments and propose a set of approaches for hashtag segmentation by framing it as a pairwise ranking problem between candidate segmentations. Our novel neural approaches demonstrate 24.6{\\%} error reduction in hashtag segmentation accuracy compared to the current state-of-the-art method. Finally, we demonstrate that a deeper understanding of hashtag semantics obtained through segmentation is useful for downstream applications such as sentiment analysis, ",
 "signal": "permissive",
 "reason": "The declared licence (agpl-3.0) is classified as share-alike.",
 "revision": "926842c8fbeadabe99a88d30d4b7ce06a42fb64c",
 "stated_evidence": "https://huggingface.co/datasets/ruanchaves/stan_large/blob/926842c8fbeadabe99a88d30d4b7ce06a42fb64c/README.md",
 "file_evidence": "https://huggingface.co/datasets/ruanchaves/stan_large/tree/926842c8fbeadabe99a88d30d4b7ce06a42fb64c",
 "card_nc": false
}