Liu Zhihui

@jind11 the training is very fast even on cpu, so you can train you own model: ```bash $ git pull [email protected]:FrankWork/acnn.git $ git pull origin baseap $ git checkout baseap...

If you can reach the performance in the paper, please let me know.

@jind11 trained on Wikipedia https://github.com/Hironsan/awesome-embedding-models https://ronan.collobert.com/senna/senna-v3.0.tgz

position feature in code is correct. https://github.com/FrankWork/conv_relation/blob/c1384e5785ab2bcc6ec2d9eaba33383d5c5de85b/src/reader/base.py#L202

关系类别，实体一的起始位置，实体一的结束位置，实体二的起始位置，实体二的结束位置

是不是你把epoch数给改了

data文件夹下是 SemEval2010 task8 数据集

@leoloee 百度一下，你就知道。https://docs.google.com/document/d/1QO_CnmvNRnYwNWu1-QCAeR5ToQYkXUqFeAJbdEhsq7w/preview

you are right. I used test dataset as the validation set.

@ShomyLiu Using the official `src/scorer.pl`, I got f1 about 82 for 50d word embed, and 83.6 for 300d word embed. My results were saved in `log` directory. How do you...