Published September 23, 2021
| Version v1
Software
Open
EDGAR-W2V Embeddings
- 1. Institute of Informatics & Telecommunications
Description
EDGAR-W2V: the word embeddings trained on EDGAR-CORPUS.
EDGAR-W2V is 200-dimensional and contains a financial vocabulary of 100k tokens, which is also attached.
EDGAR-W2V is found in the paper entitled "EDGAR-CORPUS: Billions of Tokens Make The World Go Round", Proceedings of the Workshop on Economics and Natural Language Processing (ECONLP) - co-located with EMNLP 2021
Files
edgar-w2v-200d.zip
Files
(75.4 MB)
| Name | Size | Download all |
|---|---|---|
|
md5:a1ad8cce559786edb658b594cacb7e6f
|
75.4 MB | Preview Download |