Update README.md
#7
by
sergeyfeldman
- opened
README.md
CHANGED
|
@@ -15,6 +15,8 @@ metrics:
|
|
| 15 |
|
| 16 |
SPECTER is a pre-trained language model to generate document-level embedding of documents. It is pre-trained on a powerful signal of document-level relatedness: the citation graph. Unlike existing pretrained language models, SPECTER can be easily applied to downstream applications without task-specific fine-tuning.
|
| 17 |
|
|
|
|
|
|
|
| 18 |
Paper: [SPECTER: Document-level Representation Learning using Citation-informed Transformers](https://arxiv.org/pdf/2004.07180.pdf)
|
| 19 |
|
| 20 |
Original Repo: [Github](https://github.com/allenai/specter)
|
|
|
|
| 15 |
|
| 16 |
SPECTER is a pre-trained language model to generate document-level embedding of documents. It is pre-trained on a powerful signal of document-level relatedness: the citation graph. Unlike existing pretrained language models, SPECTER can be easily applied to downstream applications without task-specific fine-tuning.
|
| 17 |
|
| 18 |
+
If you're coming here because you want to embed papers, SPECTER has now been superceded by [SPECTER 2.0](https://huggingface.co/allenai/specter_plus_plus). Use that instead.
|
| 19 |
+
|
| 20 |
Paper: [SPECTER: Document-level Representation Learning using Citation-informed Transformers](https://arxiv.org/pdf/2004.07180.pdf)
|
| 21 |
|
| 22 |
Original Repo: [Github](https://github.com/allenai/specter)
|