Update README.md

README.md

@@ -6,8 +6,8 @@ license: apache-2.0
 This model is a full precision version of the original [universal-sentence-encoder](https://tfhub.dev/google/universal-sentence-encoder/4),
 wrapped by input and output reshaping layers.
 
-These wrapping processing layers change the input and output signature from Rank-1 (Lists) to Rank-2 (Matrices),
-making the model compatible with the serving environments of the Actian Analytics Engine that requires a feature dimension of Rank-2 or higher.
+These wrapping processing layers change the input signature from Rank-1 (Lists) to Rank-2 (Matrices),
+making the model compatible with the serving environments of the Actian Analytics Engine that requires an input dimension of Rank-2 or higher.
 
 ## Description adapted from [TFHub](https://tfhub.dev/google/universal-sentence-encoder/4)