Input file

[biostanley]

XuezheMax, Could you upload the input (train,dev,test) files for run_ner_crf.sh? I read the post on issue#9, and added the word ids accordingly for each sentence from the conll2013 eng.train eng.testa/b dataset. i.e: 18 people NNS I-NP O 19 that IN I-SBAR O 20 I PRP I-NP O 21 grew VBD I-VP O but I got the following two issues: 1) assign_tensor(tensor.data, val) error until maximum recursion depth exceeded:

• NERCRF - INFO - constructing network... Traceback (most recent call last): File "examples/NERCRF.py", line 248, in main() File "examples/NERCRF.py", line 146, in main tag_space=tag_space, embedd_word=word_table, p_in=p_in, p_out=p_out, p_rnn=p_rnn, bigram=bigram, initializer=initializer) File "./neuronlp2/models/sequence_labeling.py", line 201, in init p_in=p_in, p_out=p_out, p_rnn=p_rnn, initializer=initializer) File "./neuronlp2/models/sequence_labeling.py", line 16, in init self.word_embedd = Embedding(num_words, word_dim, init_embedding=embedd_word) File "./neuronlp2/nn/modules/sparse.py", line 53, in init self.reset_parameters(init_embedding) File "./neuronlp2/nn/modules/sparse.py", line 60, in reset_parameters assign_tensor(self.weight, init_embedding) File "./neuronlp2/nn/init.py", line 17, in assign_tensor assign_tensor(tensor.data, val) File "./neuronlp2/nn/init.py", line 17, in assign_tensor assign_tensor(tensor.data, val) File "./neuronlp2/nn/init.py", line 17, in assign_tensor assign_tensor(tensor.data, val)

2) I modified the following line by if not os.path.isdir() to if os.path.isdir() to make use of the new tags out of the ner.json, will this (the folder contains ner.json which limits the tagger format) be ok? original: if not os.path.isdir(alphabet_directory): modify: if os.path.isdir(alphabet_directory): Thank you very much

[XuezheMax]

Hi, Are you using Pytorch 0.4 or o.3? If you use 0.4, please switch to branch 'pytorch4.0' For 2. I did not understand what is your goal. Would you please clarity what you want to do? Thanks.

[biostanley]

Thanks a lot for pointing out the version problem. For 2, I am trying see if the end-to-end framework can be used for other tagging problems, which contains about 15 tags (15 different type of named entities). By modifying the os.path.isdir(alphabet_directory), I want to automatically build a new tag dictionary, any suggestions on what is the best way to do this?
Will the end-to-end framework good for more than 10 tags?

[XuezheMax]

In that way, you just need to prepare your data, remove the folder containing old alphabets, and re-run the code on the new data.

On Sat, Apr 28, 2018 at 8:32 PM, biostanley notifications@github.com wrote:

Thanks a lot for pointing out the version problem. For 2, I am trying see if the end-to-end framework can be used for other tagging problems, which contains about 15 tags. By modifying the os.path.isdir(alphabet_directory), I want to automatically build a new tag dictionary, any suggestions on what is the best way to do this? Will the end-to-end framework good for more than 10 tags?

— You are receiving this because you commented. Reply to this email directly, view it on GitHub https://github.com/XuezheMax/NeuroNLP2/issues/12#issuecomment-385215439, or mute the thread https://github.com/notifications/unsubscribe-auth/ADUtltvKPpdPgz5tXF9PSUWmyX97vICkks5ttQoBgaJpZM4TrT7X .

--

Best regards, Ma，Xuezhe Language Technologies Institute, School of Computer Science, Carnegie Mellon University Tel: +1 206-512-5977