def to_method_object(self):
"""Convert the enum to an instance of `BaselineMethod`."""
if self == self.TF_IDF:
return keyword_based.TfIdfMethod()
elif self == self.BM25:
return keyword_based.BM25Method()
elif self == self.USE_SIM:
return vector_based.VectorSimilarityMethod(
encoder=vector_based.TfHubEncoder(
"https://tfhub.dev/google/"
"universal-sentence-encoder/2"))
elif self == self.USE_LARGE_SIM:
return vector_based.VectorSimilarityMethod(
encoder=vector_based.TfHubEncoder(
"https://tfhub.dev/google/"
"universal-sentence-encoder-large/3"))
elif self == self.ELMO_SIM:
return vector_based.VectorSimilarityMethod(
encoder=vector_based.TfHubEncoder(
"https://tfhub.dev/google/elmo/1"))
elif self == self.USE_MAP:
return vector_based.VectorMappingMethod(
encoder=vector_based.TfHubEncoder(
"https://tfhub.dev/google/"
"universal-sentence-encoder/2"))
elif self == self.USE_LARGE_MAP:
return vector_based.VectorMappingMethod(
encoder=vector_based.TfHubEncoder(
"https://tfhub.dev/google/"
"universal-sentence-encoder-large/3"))
elif self == self.ELMO_MAP:
return vector_based.VectorMappingMethod(
encoder=vector_based.TfHubEncoder(
"https://tfhub.dev/google/elmo/1"))
raise ValueError("Unknown method {}".format(self))
def test_train_test(self):
"""Check that it can correctly rank a simple example."""
method = keyword_based.TfIdfMethod()
method.train(["hello how are you", "hello how are"],
["hello how", "hello"])
predictions = method.rank_responses(["hello", "how", "are", "you"],
["you", "are", "how", "hello"])
self.assertEqual(list(predictions), [3, 2, 1, 0])
def test_train_test_idf(self):
"""Check that the keyword with higher idf counts for more."""
method = keyword_based.TfIdfMethod()
method.train(["hello how are you", "hello how are"],
["hello how", "hello"])
predictions = method.rank_responses(["hello you", "hello you"],
["hello", "you"])
self.assertEqual(
list(predictions),
[1, 1] # you is more informative than 'hello'.
)
def to_method_object(self):
"""Convert the enum to an instance of `BaselineMethod`."""
if self == self.TF_IDF:
return keyword_based.TfIdfMethod()
elif self == self.BM25:
return keyword_based.BM25Method()
elif self == self.USE_SIM:
return vector_based.VectorSimilarityMethod(
encoder=vector_based.TfHubEncoder(
"https://tfhub.dev/google/"
"universal-sentence-encoder/2"))
elif self == self.USE_LARGE_SIM:
return vector_based.VectorSimilarityMethod(
encoder=vector_based.TfHubEncoder(
"https://tfhub.dev/google/"
"universal-sentence-encoder-large/3"))
elif self == self.ELMO_SIM:
return vector_based.VectorSimilarityMethod(
encoder=vector_based.TfHubEncoder(
"https://tfhub.dev/google/elmo/1"))
elif self == self.USE_MAP:
return vector_based.VectorMappingMethod(
encoder=vector_based.TfHubEncoder(
"https://tfhub.dev/google/"
"universal-sentence-encoder/2"))
elif self == self.USE_LARGE_MAP:
return vector_based.VectorMappingMethod(
encoder=vector_based.TfHubEncoder(
"https://tfhub.dev/google/"
"universal-sentence-encoder-large/3"))
elif self == self.ELMO_MAP:
return vector_based.VectorMappingMethod(
encoder=vector_based.TfHubEncoder(
"https://tfhub.dev/google/elmo/1"))
elif self == self.BERT_SMALL_SIM:
return vector_based.VectorSimilarityMethod(
encoder=vector_based.BERTEncoder(
"https://tfhub.dev/google/"
"bert_uncased_L-12_H-768_A-12/1"))
elif self == self.BERT_SMALL_MAP:
return vector_based.VectorMappingMethod(
encoder=vector_based.BERTEncoder(
"https://tfhub.dev/google/"
"bert_uncased_L-12_H-768_A-12/1"))
elif self == self.BERT_LARGE_SIM:
return vector_based.VectorSimilarityMethod(
encoder=vector_based.BERTEncoder(
"https://tfhub.dev/google/"
"bert_uncased_L-24_H-1024_A-16/1"))
elif self == self.BERT_LARGE_MAP:
return vector_based.VectorMappingMethod(
encoder=vector_based.BERTEncoder(
"https://tfhub.dev/google/"
"bert_uncased_L-24_H-1024_A-16/1"))
elif self == self.USE_QA:
return vector_based.VectorSimilarityMethod(
encoder=vector_based.TfHubEncoder(
"https://tfhub.dev/google/"
"universal-sentence-encoder-multilingual-qa/1",
is_dual=True))
raise ValueError("Unknown method {}".format(self))