added models and readme in data folder

Author: danielecalda

.gitignore

@@ -1,4 +1,3 @@
 venv
 .ipynb_checkpoints
-models/
 .idea

nlp/1-ner/data/README.md

@@ -0,0 +1,15 @@
+# Data for training
+
+In this directory you can find data related with dataset [Annotated Corpus for Named Entity Recognition
+](https://www.kaggle.com/abhinavwalia95/entity-annotated-corpus?select=ner_dataset.csv) from Kaggle.
+
+In particular the dataset is present in three different format.
+
+* [iob scheme](iob_ner_dataset.csv): not used in notebooks but you can use this in place
+of biluo dataset in [bilstm ner notebook](../notebooks/bilstm%20ner.ipynb)
+* [biluo scheme](biluo_ner_dataset.csv): used in [bilstm ner notebook](../notebooks/bilstm%20ner.ipynb)
+* [jsonl scheme](ner_jsonò_dataset.pickle): used in [spacy ner notebook](../notebooks/spacy%20ner.ipynb)
+
+In this directory you can find also a notebook with code to transform dataset from a format to another.
+In particular you can transform dataset from iob to biluo scheme, from biluo scheme to jsonl format and
+vice versa.

nlp/1-ner/data/ner_dataset.csv nlp/1-ner/data/iob_ner_dataset.csv

@@ -0,0 +1,36 @@
+{
+  "lang":"en",
+  "name":"ner_model",
+  "version":"0.0.0",
+  "spacy_version":">=2.3.4",
+  "description":"",
+  "author":"",
+  "email":"",
+  "url":"",
+  "license":"",
+  "spacy_git_version":"6fb3e4796",
+  "vectors":{
+    "width":0,
+    "vectors":0,
+    "keys":0,
+    "name":"spacy_pretrained_vectors"
+  },
+  "pipeline":[
+    "ner"
+  ],
+  "factories":{
+    "ner":"ner"
+  },
+  "labels":{
+    "ner":[
+      "art",
+      "eve",
+      "geo",
+      "gpe",
+      "nat",
+      "org",
+      "per",
+      "tim"
+    ]
+  }
+}

nlp/1-ner/models/bilstm.h5

@@ -0,0 +1,18 @@
+{
+  "beam_width":1,
+  "beam_density":0.0,
+  "beam_update_prob":1.0,
+  "cnn_maxout_pieces":3,
+  "nr_feature_tokens":6,
+  "nr_class":34,
+  "hidden_depth":1,
+  "token_vector_width":96,
+  "hidden_width":64,
+  "maxout_pieces":2,
+  "pretrained_vectors":null,
+  "bilstm_depth":0,
+  "self_attn_depth":0,
+  "conv_depth":4,
+  "conv_window":1,
+  "embed_size":2000
+}

nlp/1-ner/models/index_to_tag.pickle

@@ -0,0 +1 @@
+��moves�
P{"0":{},"1":{"geo":-1,"tim":-2,"gpe":-3,"per":-4,"org":-5,"art":-6,"nat":-7,"eve":-8},"2":{"geo":-1,"tim":-2,"gpe":-3,"per":-4,"org":-5,"art":-6,"nat":-7,"eve":-8},"3":{"geo":-1,"tim":-2,"gpe":-3,"per":-4,"org":-5,"art":-6,"nat":-7,"eve":-8},"4":{"":1,"geo":-1,"tim":-2,"gpe":-3,"per":-4,"org":-5,"art":-6,"nat":-7,"eve":-8},"5":{"":1}}

nlp/1-ner/models/ner_model/meta.json

@@ -0,0 +1 @@
+�

nlp/1-ner/models/ner_model/ner/cfg

@@ -0,0 +1 @@
+��lexeme_norm�