nlp_primitives.UniversalSentenceEncoder

class nlp_primitives.UniversalSentenceEncoder

Transforms a sentence or short paragraph to a vector using [tfhub model](https://tfhub.dev/google/universal-sentence-encoder/2)

Parameters

None –

Examples

>>> universal_sentence_encoder = UniversalSentenceEncoder()
>>> sentences = ["I like to eat pizza",
...              "The roller coaster was built in 1885.",
...              ""]
>>> output = universal_sentence_encoder(sentences)
>>> len(output)
512
>>> len(output[0])
3
>>> values = output[:3, 0]
>>> [round(x, 4) for x in values]
[0.0178, 0.0616, -0.0089]

__init__()

Initialize self. See help(type(self)) for accurate signature.

Methods

__init__()	Initialize self.
generate_name(base_feature_names)
generate_names(base_feature_names)
get_args_string()
get_arguments()
get_filepath(filename)
get_function()

Attributes

base_of
base_of_exclude
commutative
default_value
input_types
max_stack_depth
name
number_output_features
uses_calc_time
uses_full_entity