diff --git a/code/config_global_1.1.json b/code/config_global_1.1.json new file mode 100644 index 0000000000000000000000000000000000000000..f0b5843e059dc39d4bfa94007c727f563cd45f56 --- /dev/null +++ b/code/config_global_1.1.json @@ -0,0 +1,50 @@ +{ + "usecase_description": "Config file for usecase_1 : from a raw text, get the same text but with EDU bracket.", + "data_raw": { + "name": "edgar_poe_en", + "exte": ".txt", + "language": "en", + "existing_metadata": true + }, + "steps":{ + "main": "annotation", + "pre-processing": { + "to_do": true, + "syntactic_tool": "stanza", + "sentence_split": true, + "tokenization": true, + "syntactic_parsing": false, + "create_metadata": { + "to_do": true, + "line": "paragraph", + "sent": "sent" + } + }, + "discourse_segmenter": { + "model": "/home/lriviere/andiamo/discut/Results_conllu/results_eng.rst.gum-eng_bert/model.tar.gz", + "training": { + "toolkit": null, + "pre_trained_lm": null, + "config_file": null, + "train_data_path": null, + "validation_data_path": null + } + }, + "evaluation": true, + "gold_test_data_path": null + }, + "output":{ + "conll_file":{ + "to_do": true, + "metadata": true, + "with_gold_labels": false + }, + "txt_file":{ + "to_do": false, + "metadata": true + } + } +} + + + diff --git a/code/config_global_2.json b/code/config_global_2.json new file mode 100644 index 0000000000000000000000000000000000000000..988e706f2314ba8f1c68d6b3531ad75b7d5bcf60 --- /dev/null +++ b/code/config_global_2.json @@ -0,0 +1,50 @@ +{ + "usecase_description": "Config file for usecase_2 : from a gold text, make predictions with an existing model, compare gold and predictions with metrics.", + "data_raw": { + "name": "eng.pdtb.pdtb_dev", + "exte": ".conllu", + "language": "en", + "existing_metadata": true + }, + "steps":{ + "main": "test", + "pre-processing": { + "to_do": false, + "syntactic_tool": "stanza", + "sentence_split": true, + "tokenization": true, + "syntactic_parsing": true, + "create_metadata": { + "to_do": true, + "line": "paragraph", + "sent": "sent" + } + }, + "discourse_segmenter": { + "model": "/home/lriviere/andiamo/morteza/discut/Results_conllu/results_eng.pdtb.pdtb_bert/model.tar.gz", + "training": { + "toolkit": null, + "pre_trained_lm": null, + "config_file": null, + "train_data_path": null, + "validation_data_path": null + } + }, + "evaluation": true, + "gold_test_data_path": null + }, + "output":{ + "conll_file":{ + "to_do": true, + "metadata": true, + "with_gold_labels": true + }, + "txt_file":{ + "to_do": true, + "metadata": true + } + } +} + + +