def get_phrases_free(question, model, nlp_path, java_path):
"""Convert a string question to list of phrases
Keyword arguments:
question -- question in string form
model -- model for phrase detection
nlp_path -- path to Stanford NLP tagger
java_path -- path to Java instalation
"""
pd_model = pickle.load(open(model))
q = Question(question, "")
utterance = question.split()
labels = []
pos = pos_tag([q])
ner = ner_tag([q], nlp_path, java_path)
l = 4
u = ["", ""] + utterance + ["", ""]
p = ['', ''] + [pp[1] for pp in pos[0]] + ['', '']
n = ['', ''] + [nn[1] for nn in ner[0]] + ['', '']
for j in range(2, len(u) - 2):
feature = construct_feature(p, u, n, j, l)
label = predict(pd_model, feature, 4)
labels.append(label)
l = label
phr, pos_t = sr.parse_to_phrases([q], [labels], pos)
candidates = el.obtain_entity_candidates(phr, 5)
return labels, pos, q, candidates
def get_phrases_free(question, model, nlp_path, java_path):
"""Convert a string question to list of phrases
Keyword arguments:
question -- question in string form
model -- model for phrase detection
nlp_path -- path to Stanford NLP tagger
java_path -- path to Java instalation
"""
pd_model = pickle.load(open(model))
q = Question(question, "")
utterance = question.split()
labels = []
pos = pos_tag([q])
ner = ner_tag([q], nlp_path, java_path)
l = 4
u = ["", ""] + utterance + ["", ""]
p = ['', ''] + [pp[1] for pp in pos[0]] + ['', '']
n = ['', ''] + [nn[1] for nn in ner[0]] + ['', '']
for j in range(2, len(u)-2):
feature = construct_feature(p, u, n, j, l)
label = predict(pd_model, feature, 4)
labels.append(label)
l = label
phr, pos_t = sr.parse_to_phrases([q], [labels], pos)
candidates = el.obtain_entity_candidates(phr, 5)
return labels, pos, q, candidates
def get_phrases(phrase, features):
"""Convert a question from the dataset to list of phrases
Keyword arguments:
question -- question in object form
features -- features for phrase detection
"""
phrases = []
for U in features:
label = predict(phrase, U, 4)
if label == 2:
label = 4
phrases.append(label)
return phrases
def get_phrases(phrase, features):
"""Convert a question from the dataset to list of phrases
Keyword arguments:
question -- question in object form
features -- features for phrase detection
"""
phrases = []
for U in features:
label = predict(phrase, U, 4)
if label == 2:
label = 4
phrases.append(label)
return phrases
def label_phrases(questions, pos_tagged, ner_tagged, weights):
"""Find phrase labels for words without knowing gold standard labels
Keyword arguments:
questions -- list of Question objects
pos_tagged -- list of lists of POS tagged words
ner_tagged -- list of lists of NER tagged words
weights -- model trained for phrase detection
"""
features = []
labels = []
for i in range(len(questions)):
l = 4
question = questions[i]
u = ["", ""]+question.utterance.split()+["", ""]
p = ['', '']+[pp[1] for pp in pos_tagged[i]]+['', '']
n = ['', '']+[nn[1] for nn in ner_tagged[i]]+['', '']
for j in range(2, len(u)-2):
f = construct_feature(p, u, n, j, l)
l = predict(weights, f, 5)
features.append(f)
labels.append(l)
return features, labels
def label_phrases(questions, pos_tagged, ner_tagged, weights):
"""Find phrase labels for words without knowing gold standard labels
Keyword arguments:
questions -- list of Question objects
pos_tagged -- list of lists of POS tagged words
ner_tagged -- list of lists of NER tagged words
weights -- model trained for phrase detection
"""
features = []
labels = []
for i in range(len(questions)):
l = 4
question = questions[i]
u = ["", ""] + question.utterance.split() + ["", ""]
p = ['', ''] + [pp[1] for pp in pos_tagged[i]] + ['', '']
n = ['', ''] + [nn[1] for nn in ner_tagged[i]] + ['', '']
for j in range(2, len(u) - 2):
f = construct_feature(p, u, n, j, l)
l = predict(weights, f, 5)
features.append(f)
labels.append(l)
return features, labels