riva/proto/riva_nlp_pipeline.proto
riva/proto/riva_nlp_pipeline.proto¶
-
message TextClassificationInput¶
-
string sentence¶
Sentence to classify
-
string classes(repeated)¶
Possible class labels to classify the sequence into
-
string hypothesis_template¶
The template used to turn each label into an NLI-style hypothesis. Template must include a {}. Default: “This example is {}.”
-
bool multi_class¶
Whether or not multiple candidate labels can be true. If False, then the scores are normalized such that the sum of the label likelihoods for each sequence is 1. If True, then the labels are considered independent and probabilities are normalized for each candidate by doing a softmax of the entailment score vs. the contradiction score.
-
string sentence¶
-
message TextClassificationOutput¶
-
string sentence¶
Sentence which was classified
-
ClassScore scores(repeated)¶
Class scores
-
string sentence¶