Prompsit
/

paraphrase-bert-en

Text Classification

text-embeddings-inference

Model card Files Files and versions

gramirez-prompsit commited on Dec 14, 2021

Commit

1a86eb3

·

1 Parent(s): 41f52fb

Update README.md

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -15,7 +15,7 @@ Model built under a TSI-100905-2019-4 project, co-financed by Ministry of Econom
 # How to use it
-The model answer the following question: Is "phrase B" paraphrases of "phrase A".
 Please note that we're considering phrases instead of sentences. Therefore, we must take into account that the model doesn't expect to find punctuation marks or long pieces of text.
 Resulting probabilities correspond to classes:
@@ -41,4 +41,4 @@ Code output is:
  ```
  tensor([[0.1592, 0.8408]], grad_fn=<SoftmaxBackward>)
  ```
-As the probability of 1 is 0.84, we can conclude from the previous example that "could be included" is paraphrase of "may be included".

 # How to use it
+The model answer the following question: Is "phrase B" a paraphrase of "phrase A".
 Please note that we're considering phrases instead of sentences. Therefore, we must take into account that the model doesn't expect to find punctuation marks or long pieces of text.
 Resulting probabilities correspond to classes:
  ```
  tensor([[0.1592, 0.8408]], grad_fn=<SoftmaxBackward>)
  ```
+As the probability of 1 is 0.84, we can conclude from the previous example that "could be included" is paraphrase of "may be addressed".