116 lines
4.5 KiB
Python
116 lines
4.5 KiB
Python
from conllu import parse_incr
|
|
from flair.data import Corpus, Sentence, Token
|
|
from flair.datasets import SentenceDataset
|
|
from flair.embeddings import StackedEmbeddings
|
|
from flair.embeddings import WordEmbeddings
|
|
from flair.embeddings import CharacterEmbeddings
|
|
from flair.embeddings import FlairEmbeddings
|
|
from flair.models import SequenceTagger
|
|
from flair.trainers import ModelTrainer
|
|
import random
|
|
import torch
|
|
import os
|
|
|
|
|
|
class NLU:
|
|
def __init__(self):
|
|
self.model = None
|
|
|
|
def nolabel2o(self, line, i):
|
|
return 'O' if line[i] == 'NoLabel' else line[i]
|
|
|
|
def conllu2flair(self, sentences, label=None):
|
|
fsentences = []
|
|
for sentence in sentences:
|
|
fsentence = Sentence()
|
|
for token in sentence:
|
|
ftoken = Token(token['form'])
|
|
if label:
|
|
ftoken.add_tag(label, token[label])
|
|
fsentence.add_token(ftoken)
|
|
fsentences.append(fsentence)
|
|
return SentenceDataset(fsentences)
|
|
|
|
def load_model(self, model_path):
|
|
self.model = SequenceTagger.load(model_path)
|
|
|
|
def train_model(self, train_path, test_path):
|
|
fields = ['id', 'form', 'frame', 'slot']
|
|
|
|
with open(train_path, encoding='utf-8') as trainfile:
|
|
trainset = list(parse_incr(trainfile, fields=fields, field_parsers={'slot': self.nolabel2o}))
|
|
with open(test_path, encoding='utf-8') as testfile:
|
|
testset = list(parse_incr(testfile, fields=fields, field_parsers={'slot': self.nolabel2o}))
|
|
|
|
random.seed(42)
|
|
torch.manual_seed(42)
|
|
|
|
if torch.cuda.is_available():
|
|
torch.cuda.manual_seed(0)
|
|
torch.cuda.manual_seed_all(0)
|
|
torch.backends.cudnn.enabled = False
|
|
torch.backends.cudnn.benchmark = False
|
|
torch.backends.cudnn.deterministic = True
|
|
|
|
corpus = Corpus(train=self.conllu2flair(trainset, 'slot'), test=self.conllu2flair(testset, 'slot'))
|
|
|
|
tag_dictionary = corpus.make_tag_dictionary(tag_type='slot')
|
|
|
|
embedding_types = [
|
|
WordEmbeddings('pl'),
|
|
FlairEmbeddings('pl-forward'),
|
|
FlairEmbeddings('pl-backward'),
|
|
CharacterEmbeddings(),
|
|
]
|
|
|
|
embeddings = StackedEmbeddings(embeddings=embedding_types)
|
|
tagger = SequenceTagger(hidden_size=256, embeddings=embeddings,
|
|
tag_dictionary=tag_dictionary,
|
|
tag_type='slot', use_crf=True)
|
|
|
|
if not os.path.isdir('slot-model-pl'):
|
|
trainer = ModelTrainer(tagger, corpus)
|
|
trainer.train('slot-model-pl',
|
|
learning_rate=0.1,
|
|
mini_batch_size=32,
|
|
max_epochs=10,
|
|
train_with_dev=True)
|
|
|
|
try:
|
|
self.load_model('slot-model-pl/best-model.pt')
|
|
except:
|
|
self.load_model('slot-model-pl/final-model.pt')
|
|
|
|
# Tworzenie osobnego pliku z metrykami dla modelu
|
|
log_file = open('slot-model-pl/training.log', encoding='utf-8')
|
|
log_lines = log_file.readlines()
|
|
log_file.close()
|
|
with open('slot-model-pl/training.log', encoding='utf-8') as log_file, open('evaluation.txt', 'w',
|
|
encoding='utf-8') \
|
|
as eval_file:
|
|
for num, line in enumerate(log_file):
|
|
if line == 'Results:\n':
|
|
lines_to_write_start = num
|
|
eval_file.write('*** This evaluation file was generated automatically by the training script ***\n\n')
|
|
for line in log_lines[lines_to_write_start:]:
|
|
eval_file.write(line)
|
|
|
|
def predict(self, sentence):
|
|
sentence = sentence.split()
|
|
csentence = [{'form': word} for word in sentence]
|
|
fsentence = self.conllu2flair([csentence])[0]
|
|
self.model.predict(fsentence)
|
|
return [(token, ftoken.get_tag('slot').value) for token, ftoken in zip(sentence, fsentence)]
|
|
|
|
|
|
# Można przetestować...
|
|
# nlu = NLU()
|
|
# nlu.train_model('train-pl.conllu', 'test-pl.conllu')
|
|
# lub
|
|
# nlu.load_model('slot-model-pl/final-model.pt')
|
|
# print(nlu.predict("Poproszę jeden bilet na film Batman na imię Jan Kowalski"))
|
|
|
|
# Zwrócone:
|
|
# [('Poproszę', 'O'), ('jeden', 'O'), ('bilet', 'O'), ('na', 'O'), ('film', 'O'), ('Batman', 'B-movie'),
|
|
# ('na', 'O'), ('imię', 'O'), ('Jan', 'B-name'), ('Kowalski', 'I-name')]
|