def test_hmm_count_correct():
sentence = "Tamir the AP comes this story :"
tags = "PROPN DET PROPN VERB DET NOUN PUNCT"
gold_sentence = [(sentence.split()[i], tags.split()[i])
for i in range(len(sentence.split()))]
sentences = tagger.load_annotated_corpus(
'trainTestData/en-ud-train.upos.tsv')
allTagCounts, perWordTagCounts, transitionCounts, emissionCounts, A, B = tagger.learn_params(
sentences)
pred_sentence = tagger.hmm_tag_sentence(sentence.split(), A, B)
correct, correctOOV, OOV = tagger.count_correct(gold_sentence,
pred_sentence)
print(correct, correctOOV, OOV)
def test_tag_sentence():
sentence = "Tamir the AP comes this story :"
sentences = tagger.load_annotated_corpus(
'trainTestData/en-ud-train.upos.tsv')
allTagCounts, perWordTagCounts, transitionCounts, emissionCounts, A, B = tagger.learn_params(
sentences)
# Models that must be supported (you can add more):
baseline = {'baseline': [perWordTagCounts, allTagCounts]}
HMM = {'hmm': [A, B]}
Vanilla_BiLSTM = {'blstm': [{}]}
BiLSTM_case = {'cblstm': [{}]}
print(tagger.tag_sentence(sentence.split(), baseline))
print(tagger.tag_sentence(sentence.split(), HMM))
print(tagger.tag_sentence(sentence.split(), Vanilla_BiLSTM))
print(tagger.tag_sentence(sentence.split(), BiLSTM_case))
import tagger
train_path = r"C:\src\MastersCourses\NLP\Assign_4\data\en-ud-train.upos.tsv"
dev_path = r"C:\src\MastersCourses\NLP\Assign_4\data\en-ud-dev.upos.tsv"
train_data = tagger.load_annotated_corpus(train_path)
dev_data = tagger.load_annotated_corpus(dev_path)
[allTagCounts, perWordTagCounts, transitionCounts, emissionCounts, A,
B] = tagger.learn_params(train_data)
gold_sentence = dev_data[0]
pred_sentence = [w[0] for w in gold_sentence]
print(f"tested sentence is {gold_sentence} of length {len(pred_sentence)}")
tagged_sentence = tagger.baseline_tag_sentence(pred_sentence, perWordTagCounts,
allTagCounts)
correct, correctOOV, OOV = tagger.count_correct(gold_sentence, tagged_sentence)
print(f"correct: {correct}, correctOOV: {correctOOV}, OOV: {OOV}")
score_nom, score_denom = 0, 0
for gold_sentence in dev_data:
pred_sentence = [w[0] for w in gold_sentence]
tagged_sentence = tagger.baseline_tag_sentence(pred_sentence,
perWordTagCounts,
allTagCounts)
correct, correctOOV, OOV = tagger.count_correct(gold_sentence,
tagged_sentence)
score_nom += correct
score_denom += len(pred_sentence)
def test_learn_params(sentences):
allTagCounts, perWordTagCounts, transitionCounts, emissionCounts, A, B = tagger.learn_params(
sentences)
return allTagCounts, perWordTagCounts, transitionCounts, emissionCounts, A, B
def check_sampled_sentence(gold_sentence, model_dict):
pred_sentence = [w[0] for w in gold_sentence]
tagged_sentence = tag_sentence(pred_sentence, model_dict)
correct, correctOOV, OOV = count_correct(gold_sentence, tagged_sentence)
print(f"correct: {correct}, correctOOV: {correctOOV}, OOV: {OOV}\n")
train_path = r"en-ud-train.upos.tsv"
dev_path = r"en-ud-dev.upos.tsv"
train_data = load_annotated_corpus(train_path)
dev_data = load_annotated_corpus(dev_path)
[allTagCounts, perWordTagCounts, transitionCounts, emissionCounts, A,
B] = learn_params(train_data)
# draw random sentence
gold_sentence = dev_data[randrange(len(dev_data))]
print(
f"tested random sentence is {gold_sentence} of length {len(gold_sentence)}\n"
)
# test baseline
calc_score(dev_data, {'baseline': [perWordTagCounts, allTagCounts]})
check_sampled_sentence(gold_sentence,
{'baseline': [perWordTagCounts, allTagCounts]})
# test hmm
calc_score(dev_data, {'hmm': [A, B]})
check_sampled_sentence(gold_sentence, {'hmm': [A, B]})