snunlp commited on
Commit
7c66e9a
1 Parent(s): 186e3de

Create README.md

Browse files
Files changed (1) hide show
  1. README.md +17 -0
README.md ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - ko
4
+
5
+ ---
6
+
7
+ # KR-FinBert & KR-FinBert-SC
8
+
9
+ Much progress has been made in the NLP (Natural Language Processing) field, with numerous studies showing that domain adaptation using small-scale corpus and fine-tuning with labeled data is effective for overall performance improvement.
10
+ we proposed KR-FinBert for the financial domain by further pre-training it on a financial corpus and fine-tuning it for sentiment analysis. As many studies have shown, the performance improvement through adaptation and conducting the downstream task was also clear in this experiment. 
11
+
12
+ ![KR-FinBert](https://huggingface.co/snunlp/KR-FinBert/resolve/main/images/KR-FinBert.png)
13
+
14
+ ## Data
15
+
16
+ The training data for this model is expanded from those of **KR-BERT-MEDIUM**, texts from Korean Wikipedia, general news articles, legal texts crawled from the National Law Information Center and [Korean Comments dataset](https://www.kaggle.com/junbumlee/kcbert-pretraining-corpus-korean-news-comments). For the transfer learning, **corporate related economic news articles from 72 media sources** such as the Financial Times, The Korean Economy Daily, etc and **analyst reports from 16 securities companies** such as Kiwoom Securities, Samsung Securities, etc are added. Included in the dataset is 440,067 news titles with their content and 11,237 analyst reports. **The total data size is about 13.22GB.** For mlm training, we split the data line by line and **the total no. of lines is 6,379,315.**
17
+ KR-FinBert is trained for 5.5M steps with the maxlen of 512, training batch size of 32, and learning rate of 5e-5, taking 67.48 hours to train the model using NVIDIA TITAN XP.