averyliu / td-dmn Goto Github PK

作者您好，我尝试邮件联系您，向您要一下LDC相关数据集处理后的数据集，但是发现您论文中给的邮箱地址错误，能否给一下可用的邮箱地址，谢谢了

Thank you for releasing the source code for TD-DMN.

Would you kindly send me the data split used in the 5-fold experiment? I have license for ACE 2005 and sent email to [email protected]. My email address is [email protected].

Thank you and look forward to your reply.

Hi, the email address([email protected]) in your paper doesn't seem to be available. So I can't show my license to you. Could you please give me a valid email address?

你好，我看了你的论文以源码。文章在3.2中有提到“The second observation is that increasing number of hops improves model performance, this further implies that processing the context for multiple times does better exploit the context. ”，可是config,py的num_of_pass值为1，这是怎么回事呀，谢谢回答。（我本科也是哈工大软工，留校读研了，跟学长做的方向相近，希望你能为我解答，谢谢）

I have the ACE2005 data. Can you give me a processed tsv data as example．let me know the style.Thank you