chqiwang/convseg

Convolutional neural network and word embeddings for Chinese word segmentation

convseg's Issues

Question about Batch Normalization?

Thanks for your code. But I have a question about the implementation af Batch Normalization.

if use_bn: w = layers.batch_norm(inputs=v, decay=0.9, is_training=is_train, center=True, scale=True, scope='BatchNorm_w_%d' % i) v = layers.batch_norm(inputs=w, decay=0.9, is_training=is_train, center=True, scale=True, scope='BatchNorm_v_%d' % i)
Where w is computed by the inputs=v and v is computed by the inputs=w. Is there a mistake? The correct code I think is
if use_bn: w = layers.batch_norm(inputs=w, decay=0.9, is_training=is_train, center=True, scale=True, scope='BatchNorm_w_%d' % i) v = layers.batch_norm(inputs=v, decay=0.9, is_training=is_train, center=True, scale=True, scope='BatchNorm_v_%d' % i)
Is it true?

Any optimization at the neg_log_likelihood computation?

Thanks for your brilliant job.

I am currently looking at building it on my own with pytorch.

Sorry that I am relatively new to NLP and thereby (maybe) immature on some issue. When the loss function looks like computationally expensive. Like, if I have a 28-char sentence and apply 4 tags as yours in the paper. I would definitely have 4^28 = 72057594037927936 results to take in. Is it really so expensive? Or there might be some form of optimization to avoid the daunting overhead?

What does the max_length mean?

What does the max_length mean in
def data_iterator(inputs, batch_size, shuffle=True, max_length=200):

IOError: [Errno 2] No such file or directory: 'model-wemb-msr/logs/dev/1.temp'

When I use word ebedding(word_window==4), I encountered this error ：

Traceback (most recent call last):
File "train.py", line 91, in
max_epoches=args.max_epoches)
File "/home/czy/Pycode/MasterPaper/code/convseg-master/tagger.py", line 440, in train
log_dir + '/dev', epoch)
File "/home/czy/Pycode/MasterPaper/code/convseg-master/cws.py", line 181, in evaluator
eval_lines = [l.rstrip() for l in codecs.open(temp_path, 'r', 'utf8')]
File "/home/czy/env/.virtualenvs/keras/lib/python2.7/codecs.py", line 896, in open
file = builtin.open(filename, mode, buffering)
IOError: [Errno 2] No such file or directory: 'model-wemb-msr/logs/dev/1.temp'

Can you tell me how to solve this problem? Thanks!

how about your evaluation metrics?

precision?or recall ?or F?

How to use the trained model for sentence segment?

Could you please show me how to segment sentence by the trained model? Thanks.

How to discuss new words?

Thanks.

Can I add a custom dictionary?

If can, how? Thanks.

参数问题

请问那个train.py里面的TASK参数应该写什么呢？我看参数定义里面没有写默认值。谢谢！

meet some problem in train.py

When i run the code train.py

Problem:
TASK = import("args")
AttributeError: module 'args' has no attribute 'read_train_file'