sanmusunrise / npns Goto Github PK

Hello：can you provide ace pre-propress tools？Thank you very much!

您好，感谢您所做的工作，我通过邮件联系了您想获取一份数据处理文件，但是没有得到回音，担心您的学校邮箱可能已经不再使用了，因此来询问一下，打扰之处请见谅。

ub16hp@UB16HP:~/ub16_prj/NPNs/src$ python NPN_TS.py kbp_config.cfg
2018-12-04 20:07:50.388605: I tensorflow/core/platform/cpu_feature_guard.cc:137] Your CPU supports instructions that this TensorFlow binary was not compiled to use: SSE4.1 SSE4.2 AVX AVX2 FMA
2018-12-04 20:07:50.449166: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:892] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2018-12-04 20:07:50.449441: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1030] Found device 0 with properties:
name: GeForce GTX 950M major: 5 minor: 0 memoryClockRate(GHz): 1.124
pciBusID: 0000:01:00.0
totalMemory: 3.95GiB freeMemory: 147.38MiB
2018-12-04 20:07:50.449465: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1120] Creating TensorFlow device (/device:GPU:0) -> (device: 0, name: GeForce GTX 950M, pci bus id: 0000:01:00.0, compute capability: 5.0)
Traceback (most recent call last):
File "NPN_TS.py", line 416, in
model.load_data_and_embedding()
File "NPN_TS.py", line 387, in load_data_and_embedding
self.train_data = EEData("train", self.configure)
File "/home/ub16hp/ub16_prj/NPNs/src/EEData.py", line 42, in init
self.load(split)
File "/home/ub16hp/ub16_prj/NPNs/src/EEData.py", line 229, in load
self.load_label2id(label2id_file)
File "/home/ub16hp/ub16_prj/NPNs/src/EEData.py", line 244, in load_label2id
for line in open(file_name):
IOError: [Errno 2] No such file or directory: '../kbp_data/label2id.dat'

src.EEData.add_data_to_batch从data_tuple中获取anchor，这个anchor是指什么？人工标注的触发词在文本中的位置吗？我没有这个数据集，作者能不能提供一下输入数据集的几条样例？谢谢。

Hi,
very brilliant jobs, can you provide the datasets preprocessing code? thanks!

学长您好，首先感谢您开源这份代码，我从中收益颇丰，然而我对NPN_TS.py的其中一行有疑惑：

请问该行是否是文章中提到的dynamic_pooling的实现？如果是的话为何只有一个reduce_max而不是根据candidate_trigger进行分段max_pooling呢？

如题