From ecbd8b76733a05eac0a19f3a4d88f9c2219ec4f8 Mon Sep 17 00:00:00 2001
From: "laura.riviere" <laura.riviere@irit.fr>
Date: Tue, 3 Jan 2023 13:33:52 +0100
Subject: [PATCH] update readme
---
code/config_global_1.json | 37 -------------------------------------
code/config_global_2.json | 38 --------------------------------------
code/config_global_3.json | 38 --------------------------------------
3 files changed, 113 deletions(-)
delete mode 100644 code/config_global_1.json
delete mode 100644 code/config_global_2.json
delete mode 100644 code/config_global_3.json
diff --git a/code/config_global_1.json b/code/config_global_1.json
deleted file mode 100644
index e767ec2..0000000
--- a/code/config_global_1.json
+++ /dev/null
@@ -1,37 +0,0 @@
-{
- "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
- }
-}
-
-
diff --git a/code/config_global_2.json b/code/config_global_2.json
deleted file mode 100644
index c720ae7..0000000
--- a/code/config_global_2.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
- "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
- }
-}
-
-
diff --git a/code/config_global_3.json b/code/config_global_3.json
deleted file mode 100644
index 67d7e8d..0000000
--- a/code/config_global_3.json
+++ /dev/null
@@ -1,38 +0,0 @@
-{
- "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"
- }
-}
-
-
--
GitLab