Skip to content
Snippets Groups Projects
Commit ecbd8b76 authored by laura.riviere's avatar laura.riviere
Browse files

update readme

parent e12e3a19
No related branches found
No related tags found
1 merge request!3Refacto 1205
{
"usecase_description": "Config file for usecase_1 : from a text, get the same text but with EDU bracket.",
"input": {
"name": "eng_annotation",
"file": ".conllu",
"language": "en"
},
"steps":{
"main": "annotation",
"pre-processing": {
"tokenization": false,
"tokenization_tool" : null,
"sentence_split": false,
"sentence_split_splitor": null,
"syntactic_parsing": false,
"NER_format_initialisation": true
},
"discourse_segmenter": {
"model": "/home/lriviere/andiamo/discut22/data/eng.sdrt.stac/results_2022-11-21_15_42_42.923648/model.tar.gz",
"training": {
"toolkit": null,
"pre_trained_lm": null,
"config_file": null,
"train_data_path": null,
"validation_data_path": null
}
},
"post-processing": {
"json_to_tab": true,
"tab_to_bracket":true
},
"evaluation": false,
"gold_test_data_path": null
}
}
{
"usecase_description": "Config file for usecase_2",
"input": {
"name": "fra.sdrt.annodis_dev",
"file": ".conllu",
"language": "fr"
},
"steps":{
"main": "test",
"pre-processing": {
"tokenization": false,
"tokenization_tool" : "spacy",
"sentence_split": false,
"sentence_split_splitor": "stanza",
"syntactic_parsing": false,
"NER_format_initialisation": true
},
"discourse_segmenter": {
"model": "tony",
"training": {
"toolkit": null,
"pre_trained_lm": null,
"config_file": null,
"train_data_path": null,
"validation_data_path": null
}
},
"post-processing": {
"json_to_tab": true,
"metadata_conll": true,
"tab_to_bracket":true
},
"evaluation": true,
"gold_test_data_path": null
}
}
{
"usecase_description": "Config file for usecase_3 : Take a EDU gold segmented set of train/dev/test of texts au format conll as input, train a model, output scores.",
"input": {
"name": "eng.sdrt.stac",
"file": ".conllu",
"language": "en"
},
"steps":{
"main": "train",
"pre-processing": {
"tokenization": false,
"tokenization_tool" : null,
"sentence_split": false,
"sentence_split_splitor": null,
"syntactic_parsing": false,
"NER_format_initialisation": true
},
"discourse_segmenter": {
"model": null,
"training": {
"toolkit": "allennlp",
"pre_trained_lm": "bert",
"config_file": "../model/config_training_bert.jsonnet",
"train_data_path": "../data/eng.sdrt.stac/eng.sdrt.stac_train.conllu",
"validation_data_path": "../data/eng.sdrt.stac/eng.sdrt.stac_dev.conllu"
}
},
"post-processing": {
"json_to_tab": false,
"metadata_conll": false,
"tab_to_bracket":false
},
"evaluation": true,
"gold_test_data_path": "../data/eng.sdrt.stac/eng.sdrt.stac_test.conllu"
}
}
0% Loading or .
You are about to add 0 people to the discussion. Proceed with caution.
Please register or to comment