nary-grn

nary-grn copied to clipboard

python 2 to python 3

1

Hi @freesunshine0316 , Thanks for sharing! Would you consider upgrading your code to python 3? When I executed the code in different versions (python 2 and python 3), the results...

wt123u

Flat indices does not index into param

7

Hi, I am trying to run your implementation of Peng's model, and I came across with the problem of the wrong input indices, shown as the image below, which made...

bhcsayx

How to configure the experiment environment?

1

jodie-kang

hanrong11

Generation of data set.

2

Hey freesunshine0316, Can you explain to me, how the in every instance of data observation you created the "arc" feature from the dependency parser. inst[u'sentences'][0][u'nodes'][9][u'arcs'] . It will be a...

VV1266

Why is there such a big difference between the results of the test set and the dev set?

2

Hello, I use data file 1 as the test set, the rest for the train set, class_num=2, max_epoch=50, the dev result can be 88, but the test result only can...

zll666

Import the dataset

1

Hi, I found that the dataset of Peng has been partially pre-processed. How can I import it into pytorch and use it immediately? I hope to use it to train...

speedhawk

how to run it

4

after modifying the train and test which should point to peng-data-file, and any else should be modifying? when i run train.sh , "AttributeError: 'Bunch' object has no attribute 'word_format'" happend....

smartcatdog

AttributeError: 'Bunch' object has no attribute 'dag_hidden_dim'

6

Number of allEdgelabels: 113 word vocab size 15736 Build DataStream ... Number of instances in trainDataStream: 5313 Number of instances in devDataStream: 200 Number of batches in trainDataStream: 665 Number...

ysn7

no attribute 'dag_hidden_dim'

1

Hi @freesunshine0316 , Thanks for sharing ! I encountered an error while running the code, as follows: nary-grn-master/bidir_dag_lstm/dag_encoder_utils.py", line 160, in __init__ w_trans = tf.get_variable("w_trans", [input_dim + edge_dim, options.dag_hidden_dim], dtype=tf.float32)...

wt123u