Files
PINE/test/data/pipelines.json
Laura Glendenning ca3266f530 Updates from latest development branch.
This includes two major features:
1. HTML view of CDA documents
2. simpletransformers-based NLP pipeline
2022-02-04 18:05:57 -05:00

55 lines
2.1 KiB
JSON

[
{
"_id": "5babb6ee4eb7dd2c39b9671c",
"title": "Apache OpenNLP Named Entity Recognition",
"description": "Apache's open source natural language processing toolkit for named entity recognition (NER). See https://opennlp.apache.org/ for more information. This is the default pipeline used for NER.",
"name": "opennlp",
"parameters": {
"cutoff": "integer",
"iterations":" integer"
}
},
{
"_id": "5babb6ee4eb7dd2c39b9671d",
"title": "SpaCy Named Entity Recognition",
"description": "spaCy is a free open-source library for Natural Language Processing in Python. It features NER, POS tagging, dependency parsing, word vectors and more",
"name": "spaCy",
"parameters": {
"n_iter": "integer",
"dropout": "float"
}
},
{
"_id": "5babb6ee4eb7dd2c39b9671f",
"title": "Stanford CoreNLP Named Entity Recognition",
"description": "Stanford's natural language processing toolkit for named entity recognition (NER). See https://stanfordnlp.github.io/CoreNLP/ for more information.",
"name": "corenlp",
"parameters": {
"max_left": "integer",
"use_class_feature": [true, false],
"use_word": [true, false],
"use_ngrams": [true, false],
"no_mid_ngrams": [true, false],
"max_ngram_length": "integer",
"use_prev": [true, false],
"use_next": [true, false],
"use_disjunctive": [true, false],
"use_sequences": [true, false],
"use_prev_sequences": [true, false],
"use_type_seqs": [true, false],
"use_type_seqs2": [true, false],
"use_type_y_sequences": [true, false]
}
},
{
"_id": "5babb6ee4eb7dd2c39b96720",
"title": "SimpleTransformers - Bio-ClinicalBERT",
"description": "SimpleTransformers models.",
"name": "simpletransformers",
"parameters": {
"training_batch_size": "integer",
"num_train_epochs": "integer"
}
}
]