Update README.md
Browse files
README.md
CHANGED
|
@@ -5,6 +5,9 @@ datasets:
|
|
| 5 |
- daily_dialog
|
| 6 |
---
|
| 7 |
|
|
|
|
|
|
|
|
|
|
| 8 |
Imaginary Embeddings utilize Curved Contrastive Learning (see paper [Imagination Is All You Need!](https://arxiv.org/pdf/2211.07591.pdf) (ACL 2023)) on [Sentence Transformers](https://sbert.net/) for long-short term dialogue planning and efficient abstract sequence modeling.
|
| 9 |
|
| 10 |
This model does not use speaker tokens and was evaluated in the Long-Term planning and sequence modeling experiments.
|
|
|
|
| 5 |
- daily_dialog
|
| 6 |
---
|
| 7 |
|
| 8 |
+
⚠️ **This model is deprecated. Please don't use it as it produces embeddings of low quality.
|
| 9 |
+
We recommend using [triple-encoders](https://huggingface.co/UKPLab/triple-encoders-dailydialog) instead, also if you want to use them as a classic bi-encoder.**
|
| 10 |
+
|
| 11 |
Imaginary Embeddings utilize Curved Contrastive Learning (see paper [Imagination Is All You Need!](https://arxiv.org/pdf/2211.07591.pdf) (ACL 2023)) on [Sentence Transformers](https://sbert.net/) for long-short term dialogue planning and efficient abstract sequence modeling.
|
| 12 |
|
| 13 |
This model does not use speaker tokens and was evaluated in the Long-Term planning and sequence modeling experiments.
|