Published November 29, 2021
| Version v1
Software
Open
SDGs_many_BERTs_SDG12
- 1. University of Southern Denmark
- 2. Vrije Universiteit Amsterdam
Description
mBERT models trained to classify targets belonging to SDG 12.
- We trained the mBERT multi-language model to classify the 169 individual SDG Targets, based on the English abstracts in the corpus of 1.4 million research papers we gathered using the Aurora SDG Query model v5.
Read more in our report: https://doi.org/10.5281/zenodo.5603019
Fork / Contribute to our code: https://github.com/Aurora-Network-Global/sdgs_many_berts
Notes
Many thanks to Maéva Vignes from University of South Denmark, to allow us to use their UCloud HPC facilities and budget to train the mBERT models on their GPU's.
[ Project website | Zenodo Community | Github ]
Files
Files
(22.1 GB)
| Name | Size | Download all |
|---|---|---|
|
md5:eb7c6e555ac91f26a11aa4ebb7914e91
|
2.0 GB | Download |
|
md5:67619596d9d3299b9c5c044611ae0ff7
|
2.0 GB | Download |
|
md5:882a7cabb0f18f691725ed63c71d8971
|
2.0 GB | Download |
|
md5:fceda77058d4202e151e0c04e018d04e
|
2.0 GB | Download |
|
md5:cc7b55db2da3fb5f5a94e2cbfb9887c3
|
2.0 GB | Download |
|
md5:c44965db2b2f2cb47d98be0848d3ae48
|
2.0 GB | Download |
|
md5:d3f056af4c46a874af3ed31a96306dd8
|
2.0 GB | Download |
|
md5:a41eb3851ae8683fcf354fce9ce93b76
|
2.0 GB | Download |
|
md5:7b58dce48c1ad467429218f5cb7bc785
|
2.0 GB | Download |
|
md5:6cec929dd139a57e72d34ed9c9bb35fc
|
2.0 GB | Download |
|
md5:58bc4956e82510d40424d66ffa9b2ed4
|
2.0 GB | Download |
Additional details
Related works
- Is documented by
- Report: 10.5281/zenodo.5603019 (DOI)