代码拉取完成,页面将自动刷新
# This script trains the BiLSTM-CRF architecture for part-of-speech tagging using
# the universal dependency dataset (http://universaldependencies.org/).
# The code use the embeddings by Komninos et al. (https://www.cs.york.ac.uk/nlp/extvec/)
from __future__ import print_function
import os
import logging
import sys
from neuralnets.BiLSTM import BiLSTM
from util.preprocessing import perpareDataset, loadDatasetPickle
# :: Change into the working dir of the script ::
abspath = os.path.abspath(__file__)
dname = os.path.dirname(abspath)
os.chdir(dname)
# :: Logging level ::
loggingLevel = logging.INFO
logger = logging.getLogger()
logger.setLevel(loggingLevel)
ch = logging.StreamHandler(sys.stdout)
ch.setLevel(loggingLevel)
formatter = logging.Formatter('%(message)s')
ch.setFormatter(formatter)
logger.addHandler(ch)
######################################################
#
# Data preprocessing
#
######################################################
datasets = {
'unidep_pos': #Name of the dataset
{'columns': {1:'tokens', 3:'POS'}, #CoNLL format for the input data. Column 1 contains tokens, column 3 contains POS information
'label': 'POS', #Which column we like to predict
'evaluate': True, #Should we evaluate on this task? Set true always for single task setups
'commentSymbol': None} #Lines in the input data starting with this string will be skipped. Can be used to skip comments
}
# :: Path on your computer to the word embeddings. Embeddings by Komninos et al. will be downloaded automatically ::
embeddingsPath = 'komninos_english_embeddings.gz'
# :: Prepares the dataset to be used with the LSTM-network. Creates and stores cPickle files in the pkl/ folder ::
pickleFile = perpareDataset(embeddingsPath, datasets)
######################################################
#
# The training of the network starts here
#
######################################################
#Load the embeddings and the dataset
embeddings, mappings, data = loadDatasetPickle(pickleFile)
# Some network hyperparameters
params = {'classifier': ['CRF'], 'LSTM-Size': [100], 'dropout': (0.25, 0.25)}
model = BiLSTM(params)
model.setMappings(mappings, embeddings)
model.setDataset(datasets, data)
model.storeResults('results/unidep_pos_results.csv') #Path to store performance scores for dev / test
model.modelSavePath = "models/[ModelName]_[DevScore]_[TestScore]_[Epoch].h5" #Path to store models
model.fit(epochs=25)
此处可能存在不合适展示的内容,页面不予展示。您可通过相关编辑功能自查并修改。
如您确认内容无涉及 不当用语 / 纯广告导流 / 暴力 / 低俗色情 / 侵权 / 盗版 / 虚假 / 无价值内容或违法国家有关法律法规的内容,可点击提交进行申诉,我们将尽快为您处理。