sergioburdisso
commited on
Commit
•
517246a
1
Parent(s):
12816ee
Update README.md
Browse files
README.md
CHANGED
@@ -17,7 +17,7 @@ base_model:
|
|
17 |
|
18 |
# Dialog2Flow joint target (DSE-base)
|
19 |
|
20 |
-
This a variation of the **D2F$_{joint}$** model introduced in the paper ["Dialog2Flow: Pre-training Soft-Contrastive Action-Driven Sentence Embeddings for Automatic Dialog Flow Extraction"](https://
|
21 |
This version uses DSE-base as the backbone model which yields to an increase in performance as compared to the vanilla version using BERT-base as the backbone (results reported in Appendix C).
|
22 |
|
23 |
Implementation-wise, this is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or search.
|
|
|
17 |
|
18 |
# Dialog2Flow joint target (DSE-base)
|
19 |
|
20 |
+
This a variation of the **D2F$_{joint}$** model introduced in the paper ["Dialog2Flow: Pre-training Soft-Contrastive Action-Driven Sentence Embeddings for Automatic Dialog Flow Extraction"](https://arxiv.org/abs/2410.18481) published in the EMNLP 2024 main conference.
|
21 |
This version uses DSE-base as the backbone model which yields to an increase in performance as compared to the vanilla version using BERT-base as the backbone (results reported in Appendix C).
|
22 |
|
23 |
Implementation-wise, this is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or search.
|