Update README.md
Browse files
README.md
CHANGED
|
@@ -2,6 +2,9 @@
|
|
| 2 |
license: apache-2.0
|
| 3 |
tags:
|
| 4 |
- ESG
|
|
|
|
|
|
|
|
|
|
| 5 |
---
|
| 6 |
## Main information
|
| 7 |
We introduce the model for multilabel ESG risks classification. There is 47 classes methodology with granularial risk definition.
|
|
@@ -80,7 +83,7 @@ tagger = Classifier.load('ner-ontonotes-large')
|
|
| 80 |
tag_list = ['FAC','LOC','ORG','PERSON']
|
| 81 |
texts_with_masks = []
|
| 82 |
for example_sent in texts:
|
| 83 |
-
|
| 84 |
word_tokens = word_tokenize(example_sent)
|
| 85 |
# converts the words in word_tokens to lower case and then checks whether
|
| 86 |
#they are present in stop_words or not
|
|
|
|
| 2 |
license: apache-2.0
|
| 3 |
tags:
|
| 4 |
- ESG
|
| 5 |
+
- finance
|
| 6 |
+
language:
|
| 7 |
+
- en
|
| 8 |
---
|
| 9 |
## Main information
|
| 10 |
We introduce the model for multilabel ESG risks classification. There is 47 classes methodology with granularial risk definition.
|
|
|
|
| 83 |
tag_list = ['FAC','LOC','ORG','PERSON']
|
| 84 |
texts_with_masks = []
|
| 85 |
for example_sent in texts:
|
| 86 |
+
filtered_sentence = []
|
| 87 |
word_tokens = word_tokenize(example_sent)
|
| 88 |
# converts the words in word_tokens to lower case and then checks whether
|
| 89 |
#they are present in stop_words or not
|