{
 "id": "bigbio/coneco",
 "owner": "bigbio",
 "name": "coneco",
 "downloads": 11,
 "likes": 2,
 "last_modified": "2024-09-06T08:17:23.000Z",
 "stated_licence": "cc-by-4.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [],
 "citation": "@article{10.1093/bioadv/vbae116,\n    author = {Nastou, Katerina and Koutrouli, Mikaela and Pyysalo, Sampo and Jensen, Lars Juhl},\n    title = \"{CoNECo: A Corpus for Named Entity Recognition and Normalization of Protein Complexes}\",\n    journal = {Bioinformatics Advances},\n    pages = {vbae116},\n    year = {2024},\n    month = {08},\n    abstract = \"{Despite significant progress in biomedical information extraction, there is a lack of resources \\\nfor Named Entity Recognition (NER) and Normalization (NEN) of protein-containing complexes. Current resources \\\ninadequately address the recognition of protein-containing complex names across different organisms, underscoring \\\nthe crucial need for a dedicated corpus.We introduce the Complex Named Entity Corpus (CoNECo), an annotated \\\ncorpus for NER and NEN of complexes. CoNECo comprises 1,621 documents with 2,052 entities, 1,976 of which are \\\nnormalized to Gene Ontology. We divided the corpus into training, development, and test sets and trained both a \\\ntransformer-based and dictionary-based tagger on them. Evaluation on the test set demonstrated robust performance, \\\nwith F-scores of 73.7\\\\% and 61.2\\\\%, respectively. Subsequently, we applied the best taggers for comprehensive \\\ntagging of the entire openly accessible biomedical literature.All resources, including the annotated corpus, \\\ntraining data, and code, are available to the community through Zenodo https://zenodo.org/records/11263147 and \\\nGitHub https://zenodo.org/records",
 "signal": "permissive",
 "reason": "The declared licence (cc-by-4.0) is classified as permissive.",
 "revision": "4eacfe5580e7a3b25c9fa57cdffb7a6c2bb5878b",
 "stated_evidence": "https://huggingface.co/datasets/bigbio/coneco/blob/4eacfe5580e7a3b25c9fa57cdffb7a6c2bb5878b/README.md",
 "file_evidence": "https://huggingface.co/datasets/bigbio/coneco/tree/4eacfe5580e7a3b25c9fa57cdffb7a6c2bb5878b",
 "card_nc": false
}