UBC-NLP
/

InfoDCL-hashtag

Feature Extraction

contrastive learning

text-embeddings-inference

Model card Files Files and versions

chiyuzhang commited on Jul 17, 2023

Commit

e6b00d8

·

1 Parent(s): c46400a

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -18,7 +18,7 @@ tags:
 [![Data License](https://img.shields.io/badge/Data%20License-CC%20By%20NC%204.0-red.svg)]()
 <p align="center" width="100%">
-    <a><img src="https://raw.githubusercontent.com/UBC-NLP/infodcl/blob/master/images/infodcl_vis.png" alt="Title" style="width: 95%; min-width: 300px; display: block; margin: auto;"></a>
 </p>
 Illustration of our proposed InfoDCL framework. We exploit distant/surrogate labels (i.e., emojis) to supervise two contrastive losses, corpus-aware contrastive loss (CCL) and Light label-aware contrastive loss (LCL-LiT). Sequence representations from our model should keep the cluster of each class distinguishable and preserve semantic relationships between classes.

 [![Data License](https://img.shields.io/badge/Data%20License-CC%20By%20NC%204.0-red.svg)]()
 <p align="center" width="100%">
+    <a><img src="https://github.com/UBC-NLP/infodcl/blob/master/images/infodcl_vis.png?raw=true" alt="Title" style="width: 95%; min-width: 300px; display: block; margin: auto;"></a>
 </p>
 Illustration of our proposed InfoDCL framework. We exploit distant/surrogate labels (i.e., emojis) to supervise two contrastive losses, corpus-aware contrastive loss (CCL) and Light label-aware contrastive loss (LCL-LiT). Sequence representations from our model should keep the cluster of each class distinguishable and preserve semantic relationships between classes.