def __init__(self, result_limit=5000, expansion=True, show_query=False):
self._expansion = expansion
self._show_query = show_query
self._linker = NameSPARQL()
self._extracter = Extraction()
self._yago = YagoTypeSimilarity()
self._query_graph = QueryGraph(result_limit)
def __init__(self, result_limit=5000, expansion=False, show_query=False):
""" semantic search of entities and concepts
:param result_limit: maximumn number of retrieved entities
:param expansion: if conduct concept expansion
:param show_query: if SPARQL query is shown
"""
self._expansion = expansion
self._show_query = show_query
self._linker = NameSPARQL()
self._extracter = Extraction()
self._yago = YagoTypeSimilarity()
self._query_graph = QueryGraph(result_limit)
def test_yago_concept_similarity():
from sematch.semantic.similarity import YagoTypeSimilarity
yagosim = YagoTypeSimilarity()
dancer = yagosim.word2yago('dancer')
actor = yagosim.word2yago('actor')
singer = yagosim.word2yago('singer')
assert yagosim.yago2synset(actor[0]) is not None
assert yagosim.yago_similarity(dancer[0], actor[0], 'wpath') is not None
assert yagosim.yago_similarity(singer[0], actor[0], 'wpath') is not None
assert yagosim.word2yago('university') is not None
assert yagosim.yago2synset(
'http://dbpedia.org/class/yago/EducationalInstitution108276342'
) is not None
assert yagosim.yago2synset(
'http://dbpedia.org/class/yago/Organization108008335') is not None
assert yagosim.yago2synset(
'http://dbpedia.org/class/yago/Institution108053576') is not None
assert yagosim.yago2synset(
'http://dbpedia.org/class/yago/Organization108008335') is not None
#using corpus-based IC from brown corpus
assert yagosim.word_similarity('dancer', 'actor', 'wpath') is not None
#using graph-based IC from DBpedia
assert yagosim.word_similarity('dancer', 'actor',
'wpath_graph') is not None
simfile.write('\n\n')
sim_ref = np.array(contents)[:, 2].astype(float) / 4.0
corr = pearson_correlation(sim_cal, sim_ref)
with open('results.txt', 'a') as resfile:
resfile.write(
'pearson correlation in dataset [%s] for FastText embedding is %f\n' %
('STS-131', corr))
# part 8
with open('datasets/stss-131.csv', newline='') as csvfile:
contents = list(csv.reader(csvfile, delimiter=';'))
from sematch.semantic.similarity import YagoTypeSimilarity
sim = YagoTypeSimilarity()
sim_cal = np.array(sentence_similarity_dataset_yago(contents,
sim)).reshape(-1, )
with open('sentence_similarity.txt', 'a') as simfile:
simfile.write('Using Yago concepts\n')
simfile.write('s1; s2; human_sim; method_sim\n\n')
for i, pair in enumerate(contents):
simfile.write('%s;%s;%s;%f\n' %
(pair[0], pair[1], pair[2], sim_cal[i] * 4))
simfile.write('\n\n')
sim_ref = np.array(contents)[:, 2].astype(float) / 4.0
corr = pearson_correlation(sim_cal, sim_ref)
with open('results.txt', 'a') as resfile:
def __init__(self):
self._linker = NameSPARQL()
self._extracter = Extraction()
self._yago = YagoTypeSimilarity()
self._query_graph = QueryGraph()
def __init__(self):
self._yago = YagoTypeSimilarity()
# ----------------------------------------------------------------
'''
Description ------------------------------------------------------------------------
Function will define YAGO concepts and calculate calculates similarity score between
sentence 1 and sentence 2 (very similar to PartialSim-function).
Inputs ------------------------------------------------------------------------------
s1 sentence 1 (string)
s2 sentence 2 (string)
method "wpath" or "wpath_graph" (string)
Outputs ----------------------------------------------------------------------------
Returns the similarity value in numeric format (between 1 and 0).
'''
#Load YAGO
sim_yago = YagoTypeSimilarity()
#Function for calculating the sentence similarities using YAGO concepts
def task4Yago(s1, s2, method):
#Format the input sentences to desired form
s1 = s1.lower()
s2 = s2.lower()
#Separate sentence into words. Aka list of words.
s1_words = word_tokenize(s1)
s2_words = word_tokenize(s2)
#POS tags for each word in sentence.
pos1 = pos_tag(s1_words)
pos2 = pos_tag(s2_words)
#Remove stop words from the pos, tagged sentences
pos1 = [word for word in pos1 if word[0] not in stopwords.words('english')]