kzjava1998/cnn-relation-extraction

Implementation of Relation Classification via Convolutional Deep Neural Network.

CNN-relation-extraction

Implementation of Relation Classification via Convolutional Deep Neural Network.

Environment Requirements

• python 3.6
• pytorch 1.3.0

Data

• SemEval2010 Task8 [paper]
• Embedding - Turian et al.(2010) [paper]

Usage

1. Download the embedding and decompress it into the embedding folder.
2. Run the following the commands to start the program.

python run.py

More details can be seen by python run.py -h.

3. You can use the official scorer to check the final predicted result.

perl semeval2010_task8_scorer-v1.2.pl proposed_answer.txt predicted_result.txt >> result.txt

Result

The result of my version and that in paper are present as follows:

paper	my version
0.789	0.7926

The training log can be seen in train.log and the official evaluation results is available in result.txt.

Note:

• Some settings are different from those mentioned in the paper.
• No validation set used during training.
• Just complete the part without lexical level features. More detail is available in Section 5.3 in this paper.
• Although I try to set random seeds, it seems that the results of each run are a little different.

Reference Link

• https://github.com/ShomyLiu/pytorch-pcnn
• https://github.com/FrankWork/conv_relation