Spaces:

Pranjal2041
/

SemSup-XC

Runtime error

App Files Files Community

Pranjal Aggarwal commited on Dec 20, 2022

Commit

0690c88

•

1 Parent(s): c4e69b4

Update

Browse files

Files changed (1) hide show

app.py +1 -1

app.py CHANGED Viewed

@@ -100,7 +100,7 @@ with gr.Blocks(css="#warning {height: 100%}") as demo:
         )
         description = "<p style='font-size: 14px; margin: 5px; font-weight: w300; text-align: center'> <a href='https://github.com/Pranjal2041' style='text-decoration:none' target='_blank'>Pranjal Aggarwal, </a> <a href='' style='text-decoration:none' target='_blank'>Ameet Deshpande, </a> <a href='' style='text-decoration:none' target='_blank'>Karthik Narasimhan </a> </p>" \
-            + "<p style='font-size: 16px; margin: 5px; font-weight: w600; text-align: center'>  <a href='https://sites.google.com/view/semsup-xc/home' target='_blank'>Project Page</a> | <a href='https://arxiv.org/abs/' target='_blank'>Arxiv</a> | <a href='https://github.com/princeton-nlp/semsup-xc' target='_blank'>Github Repo</a></p>" \
             + "<p style='text-align: center; margin: 5px; font-size: 14px; font-weight: w300;'>  \
                 Extreme classification (XC) considers the scenario of predicting over a very large number of classes (thousands to millions), with real-world applications including serving search engine results, e-commerce product tagging, and news article classification. A real-life requirement in this domain is to predict from labels unseen during training(Zero-Shot), however there have been very little success in this domain. To this end, we propose SemSup-XC, a model that achieves state-of-the-art zero-shot (ZS) and few-shot (FS) performance on three extreme classification benchmarks spanning various domains. Instead of treating labels as class ids, our model learns from diverse descriptions of them, thereby attaining a more better understanding of the label space, evident from qualitative and quantitative results.   \
                 </p>" \

         )
         description = "<p style='font-size: 14px; margin: 5px; font-weight: w300; text-align: center'> <a href='https://github.com/Pranjal2041' style='text-decoration:none' target='_blank'>Pranjal Aggarwal, </a> <a href='' style='text-decoration:none' target='_blank'>Ameet Deshpande, </a> <a href='' style='text-decoration:none' target='_blank'>Karthik Narasimhan </a> </p>" \
+            + "<p style='font-size: 16px; margin: 5px; font-weight: w600; text-align: center'>  <a href='https://sites.google.com/view/semsup-xc/home' target='_blank'>Project Page</a> | <a href='https://arxiv.org/abs/' target='_blank'>Paper</a> | <a href='https://github.com/princeton-nlp/semsup-xc' target='_blank'>Github Repo</a></p>" \
             + "<p style='text-align: center; margin: 5px; font-size: 14px; font-weight: w300;'>  \
                 Extreme classification (XC) considers the scenario of predicting over a very large number of classes (thousands to millions), with real-world applications including serving search engine results, e-commerce product tagging, and news article classification. A real-life requirement in this domain is to predict from labels unseen during training(Zero-Shot), however there have been very little success in this domain. To this end, we propose SemSup-XC, a model that achieves state-of-the-art zero-shot (ZS) and few-shot (FS) performance on three extreme classification benchmarks spanning various domains. Instead of treating labels as class ids, our model learns from diverse descriptions of them, thereby attaining a more better understanding of the label space, evident from qualitative and quantitative results.   \
                 </p>" \