darrenyaoyao / rescnn_relationextraction

Deep Residual Learning for Weakly-Supervised Relation Extraction: https://arxiv.org/abs/1707.08866

ResCNN_RelationExtraction

Deep Residual Learning for Weakly-Supervised Relation Extraction: https://arxiv.org/abs/1707.08866 By Yi Yao (Darren) Huang, William Wang

Table of Contents

0. Introduction
1. Citation
2. Model
3. Result

Introduction

This work discuss about how we solve the noise from distant supervision. We propose the Deep Residual Learning for relation extraction and mitigate the influence from the noisy in semi-supervision training data. This paper is published in EMNLP2017.

Citation

If you use this model and the concept in your research, please cite:

  @InProceedings{huang-wang:2017:EMNLP2017,
      author    = {Huang, YiYao  and  Wang, William Yang},
      title     = {Deep Residual Learning for Weakly-Supervised Relation Extraction},
      booktitle = {Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing},
      month     = {September},
      year      = {2017},
      address   = {Copenhagen, Denmark},
      publisher = {Association for Computational Linguistics},
      pages     = {1804--1808},
      url       = {https://www.aclweb.org/anthology/D17-1191}
    }

Result

vector1.txt: You can use Glove vector or Word2Vec. Here is the link I used in experiment : https://drive.google.com/open?id=0B-ZjKY509crKQXA0Y2FfbFJMY0E

rescnn_relationextraction's Issues

AttributeError: module 'tensorflow' has no attribute 'flags'

请问谁有ResCNN绘制PR曲线时的实验数据啊？感激不尽。

我的邮箱[email protected].

ValueError: setting an array element with a sequence

input_x传值错误请求大神帮助

您好，我跑了train.py，得到如下报错，谷歌了好多没有解决，希望您有空能回复下我，报错如下：
/home/lijing/Envs/information_ex/bin/python /home/lijing/Desktop/resre/ResCNN_RelationExtraction-master/ResidualCNN9/train.py

Parameters:
ALLOW_SOFT_PLACEMENT=True
BATCH_SIZE=64
CHECKPOINT_EVERY=100
DROPOUT_KEEP_PROB=0.5
EMBEDDING_DIM=50
EVALUATE_EVERY=1000
FILTER_SIZES=3
L2_REG_LAMBDA=0.0
LOG_DEVICE_PLACEMENT=False
NUM_EPOCHS=200
NUM_FILTERS=128
SEQUENCE_LENGTH=100

WordTotal= 114044
Word dimension= 1
RelationTotal: 53
Start loading training data.

Start loading testing data.

570088 96678
2017-10-09 11:13:25.942678: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE4.1 instructions, but these are available on your machine and could speed up CPU computations.
2017-10-09 11:13:25.943045: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE4.2 instructions, but these are available on your machine and could speed up CPU computations.
2017-10-09 11:13:25.943053: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use AVX instructions, but these are available on your machine and could speed up CPU computations.
2017-10-09 11:13:25.943059: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use AVX2 instructions, but these are available on your machine and could speed up CPU computations.
2017-10-09 11:13:25.943065: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use FMA instructions, but these are available on your machine and could speed up CPU computations.
Finish randomize data
Start Training
Writing to /home/lijing/Desktop/resre/ResCNN_RelationExtraction-master/ResidualCNN9/runs/1507518810

Initialize variables.
Batch data
Traceback (most recent call last):
File "/home/lijing/Desktop/resre/ResCNN_RelationExtraction-master/ResidualCNN9/train.py", line 152, in
loss = train_step(x_batch, y_batch, p1_batch, p2_batch)
File "/home/lijing/Desktop/resre/ResCNN_RelationExtraction-master/ResidualCNN9/train.py", line 110, in train_step
feed_dict)
File "/home/lijing/Envs/information_ex/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 895, in run
run_metadata_ptr)
File "/home/lijing/Envs/information_ex/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1100, in _run
% (np_val.shape, subfeed_t.name, str(subfeed_t.get_shape())))
ValueError: Cannot feed value of shape (64, 100, 1) for Tensor 'input_x:0', which has shape '(?, 100, 50)'

Process finished with exit code 1

我的环境如下：
bleach (1.5.0)
html5lib (0.9999999)
jieba (0.39)
Markdown (2.6.9)
network (0.1)
nltk (3.2.5)
numpy (1.13.3)
pip (9.0.1)
protobuf (3.4.0)
pudb (2017.1.1)
Pygments (1.3)
scikit-learn (0.19.0)
setuptools (36.5.0)
six (1.11.0)
tensorflow (1.3.0)
tensorflow-tensorboard (0.1.7)
Werkzeug (0.12.2)
wheel (0.30.0)

train时报文件不存在，请问之前data目录下有vector1.txt这个文件吗？

训练是报以下错误：
FileNotFoundError: [Errno 2] No such file or directory: '../data/vector1.txt'
请问之前data目录下有vector1.txt这个文件吗？有的话可以提供吗？谢谢！

您好，我想问一下，我在使用你的模型时，在进行预测的时候，模型的给出的预测值，总是一个固定值，没有变化，我想请问一下，这个是什么问题。

您好，我想问一下，我在使用你的模型时，在进行预测的时候，模型的给出的预测值，总是一个固定值，没有变化，我想请问一下，这个是什么问题。

Originally posted by @Mariobai in #5 (comment)

你好，我想问一下你这预测是在哪里预测的，为什么我这找不到呢？

Where is vector1.txt?

I get this error when running train.py:

FileNotFoundError: [Errno 2] No such file or directory: '../data/vector1.txt'

Where can I get vector1.txt?

请问大佬，这个链接打不开呀（vector1.txt） https://drive.google.com/open?id=0B-ZjKY509crKQXA0Y2FfbFJMY0E

Evaluation

how you evaluate the pr?
i couldn't understand your code about this part.

Why make the position embedding matrix trainable?

In line 26 in the Cnn.py file, did you mean to set trainable=True (its the default setting default).

If yes, then is there a theoretical justification for it or did you empirically find this to give the best performance?

数据处理请问

W = tf.Variable(tf.random_uniform([62, 5],
minval=-math.sqrt(6/(3position_size+3embedding_size)),
maxval=math.sqrt(6/(3position_size+3embedding_size))),
name="W")
这几行代码的功能是为了干什么啊？

Test data is not correctly loaded

ResCNN_RelationExtraction/ResidualCNN9/util/DataManager.py

Line 96 in 5449aba

if data[0]+"\t"+data[1] not in self.bags_test:

The test data should be collected for each entity pair in the map, self.bags_test (map<str, list>); however, the keys are set in a different way when a key is checked(L96). This bug effects test.py and test scores.

CURRENT : if entity1+"\t"+entity2 not in self.bags_test:
SUGGESTED : if entity1+" "+entity2 not in self.bags_test: