{
 "id": "SEACrowd/khmer_alt_pos",
 "owner": "SEACrowd",
 "name": "khmer_alt_pos",
 "downloads": 39,
 "likes": 1,
 "last_modified": "2024-06-24T13:32:36.000Z",
 "stated_licence": "cc-by-nc-sa-4.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": "cc-by-nc-sa-4.0",
 "licence_files": [
  "LICENSE"
 ],
 "sources": [],
 "gated": false,
 "tasks": [
  "pos-tagging"
 ],
 "citation": "@article{10.1145/3464378,\nauthor = {Kaing, Hour and Ding, Chenchen and Utiyama, Masao and Sumita, Eiichiro and Sam, Sethserey and Seng, Sopheap and Sudoh, Katsuhito and Nakamura, Satoshi},\ntitle = {Towards Tokenization and Part-of-Speech Tagging for Khmer: Data and Discussion},\nyear = {2021},\nissue_date = {November 2021},\npublisher = {Association for Computing Machinery},\naddress = {New York, NY, USA},\nvolume = {20},\nnumber = {6},\nissn = {2375-4699},\nurl = {https://doi.org/10.1145/3464378},\ndoi = {10.1145/3464378},\nabstract = {As a highly analytic language, Khmer has considerable ambiguities in tokenization and part-of-speech (POS) tagging processing. This topic is investigated in this study. Specifically, a 20,000-sentence Khmer corpus with manual tokenization and POS-tagging annotation is released after a series of work over the last 4 years. This is the largest morphologically annotated Khmer dataset as of 2020, when this article was prepared. Based on the annotated data, experiments were conducted to establish a comprehensive benchmark on the automatic processing of tokenization and POS-tagging for Khmer. Specifically, a support vector machine, a conditional random field (CRF), a long short-term memory (LSTM)-based recurrent neural network, and an integrated LSTM-CRF model have been investigated and discussed. As a primary conclusion, processing at morpheme-level is satisfactory for the provided data. However, it is intrinsically difficult to identify further grammatical ",
 "signal": "restrictive",
 "reason": "The declared licence (cc-by-nc-sa-4.0) is classified as having use restrictions.",
 "revision": "c00596b38c92045985220439e33be557f2e7b99e",
 "stated_evidence": "https://huggingface.co/datasets/SEACrowd/khmer_alt_pos/blob/c00596b38c92045985220439e33be557f2e7b99e/README.md",
 "file_evidence": "https://huggingface.co/datasets/SEACrowd/khmer_alt_pos/blob/c00596b38c92045985220439e33be557f2e7b99e/LICENSE",
 "card_nc": false
}