Instructions to use ESGBERT/EnvRoBERTa-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ESGBERT/EnvRoBERTa-base with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("fill-mask", model="ESGBERT/EnvRoBERTa-base")# Load model directly from transformers import AutoTokenizer, AutoModelForMaskedLM tokenizer = AutoTokenizer.from_pretrained("ESGBERT/EnvRoBERTa-base") model = AutoModelForMaskedLM.from_pretrained("ESGBERT/EnvRoBERTa-base", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit ·
c2b7c28
1
Parent(s): 8a56801
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,25 @@
|
|
| 1 |
---
|
|
|
|
| 2 |
license: apache-2.0
|
|
|
|
|
|
|
|
|
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
+
language: en
|
| 3 |
license: apache-2.0
|
| 4 |
+
tags:
|
| 5 |
+
- ESG
|
| 6 |
+
- environmental
|
| 7 |
---
|
| 8 |
+
|
| 9 |
+
# Model Card for EnvRoBERTa-base
|
| 10 |
+
|
| 11 |
+
## Model Description
|
| 12 |
+
|
| 13 |
+
This is the EnvRoBERTa-base language model. A language model that is trained to better understand environmental texts in the ESG domain.
|
| 14 |
+
|
| 15 |
+
Using the [RoBERTa](https://huggingface.co/roberta-base) model as a starting point, the EnvRoBERTa-base Language Model is additionally pre-trained on a text corpus comprising environmental-related annual reports, sustainability reports, and corporate and general news.
|
| 16 |
+
|
| 17 |
+
More details can be found in the paper:
|
| 18 |
+
```bibtex
|
| 19 |
+
@article{Schimanski23ESGBERT,
|
| 20 |
+
title={{Bridiging the Gap in ESG Measurement: Using NLP to Quantify Environmental, Social, and Governance Communication}},
|
| 21 |
+
author={Tobias Schimanski and Andrin Reding and Nico Reding and Julia Bingler and Mathias Kraus and Markus Leippold},
|
| 22 |
+
year={2023}
|
| 23 |
+
}
|
| 24 |
+
```
|
| 25 |
+
|