Raj-Sanjay-Shah
commited on
Commit
·
4b9690b
1
Parent(s):
4b55848
Update README.md
Browse files
README.md
CHANGED
@@ -6,6 +6,7 @@ tags:
|
|
6 |
widget:
|
7 |
- text: "Stocks rallied and the British pound <mask>."
|
8 |
---
|
|
|
9 |
## FLANG
|
10 |
FLANG is a set of large language models for Financial LANGuage tasks. These models use domain specific pre-training with preferential masking to build more robust representations for the domain. The models in the set are:\
|
11 |
[FLANG-BERT](https://huggingface.co/SALT-NLP/FLANG-BERT)\
|
@@ -16,8 +17,18 @@ FLANG is a set of large language models for Financial LANGuage tasks. These mode
|
|
16 |
|
17 |
## FLANG-DistilBERT
|
18 |
FLANG-DistilBERT is a pre-trained language model which uses financial keywords and phrases for preferential masking of domain specific terms. It is built by further training the DistilBERT language model in the finance domain with improved performance over previous models due to the use of domain knowledge and vocabulary.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
19 |
## Citation
|
20 |
-
Please cite the
|
21 |
```bibtex
|
22 |
@INPROCEEDINGS{shah-etal-2022-flang,
|
23 |
author = {Shah, Raj Sanjay and
|
|
|
6 |
widget:
|
7 |
- text: "Stocks rallied and the British pound <mask>."
|
8 |
---
|
9 |
+
|
10 |
## FLANG
|
11 |
FLANG is a set of large language models for Financial LANGuage tasks. These models use domain specific pre-training with preferential masking to build more robust representations for the domain. The models in the set are:\
|
12 |
[FLANG-BERT](https://huggingface.co/SALT-NLP/FLANG-BERT)\
|
|
|
17 |
|
18 |
## FLANG-DistilBERT
|
19 |
FLANG-DistilBERT is a pre-trained language model which uses financial keywords and phrases for preferential masking of domain specific terms. It is built by further training the DistilBERT language model in the finance domain with improved performance over previous models due to the use of domain knowledge and vocabulary.
|
20 |
+
|
21 |
+
## FLUE
|
22 |
+
FLUE (Financial Language Understanding Evaluation) is a comprehensive and heterogeneous benchmark that has been built from 5 diverse financial domain specific datasets.
|
23 |
+
|
24 |
+
Sentiment Classification: [Financial PhraseBank](https://huggingface.co/datasets/financial_phrasebank)\
|
25 |
+
Sentiment Analysis, Question Answering: [FiQA 2018](https://huggingface.co/datasets/SALT-NLP/FLUE-FiQA)\
|
26 |
+
New Headlines Classification: [Headlines](https://www.kaggle.com/datasets/daittan/gold-commodity-news-and-dimensions)\
|
27 |
+
Named Entity Recognition: [NER](https://huggingface.co/datasets/SALT-NLP/FLUE-NER)\
|
28 |
+
Structure Boundary Detection: [FinSBD3](https://huggingface.co/datasets/SALT-NLP/FLUE-SBD)
|
29 |
+
|
30 |
## Citation
|
31 |
+
Please cite the work with the following citation:
|
32 |
```bibtex
|
33 |
@INPROCEEDINGS{shah-etal-2022-flang,
|
34 |
author = {Shah, Raj Sanjay and
|