hkust-knowcomp/cfet

cfet's Issues

train dev test split for the cfet dataset

Hi, I'm trying to set up some experiments on your dataset. Can you share your train, dev, test split on the crowdsourced data as I would like to compare results to your paper?

How to use this model?

Hello, i am very interesting your work, can you tell me, how to use this model,thank you vert much!

下载资料失效了求更新

5555

可以维护一下下载链接吗

感谢

Looking forward to your reply.

Dear authors,
Thank you for your article "A Chinese Corpus for Fine-grained Entity Typing" for providing data sets and codes for studying Chinese fine-grained entity classification, but I would like to ask you some questions. Please feel free to enlighten me. I downloaded your code on GitHub, but I cannot reproduce the experiment in the paper, mainly because I don’t know how to generate some files needed in the code, such as glove_tokenizer$vecs.pkl, fasttext_tokenizer$vecs.pkl, etc., since what I downloaded in these two papers and other links is not a ‘pkl' file, I don’t know how the ‘pkl' files you need in your code is generated? In addition, the dataset I downloaded is in ‘json' format, but how are the data sets train.pkl, dev.pkl, and test.pkl generated in the code?

I am really interested in Chinese fine-grained entity classification and look forward to your reply, thank you!
Also, your email addresses are disabled, can you give me a new address?

作者您好！感谢您的文章“A Chinese Corpus for Fine-grained Entity Typing”为研究中文细粒度实体分类提供了数据集和代码，但是有些问题想向您请教一下，还请不吝赐教。我下载了你们在GitHub上的代码，但我无法复现论文中的实验，主要是我不知道代码中需要的一些文件时如何产生的，比如glove_tokenizer$vecs.pkl, fasttext_tokenizer$vecs.pkl等，因为我在这两篇论文等链接中下到的不是pkl文件，不知道您代码中需要的pkl文件是怎样生成的呢？另外我下载了数据集是json格式，但代码中的数据集train.pkl, dev.pkl, test.pkl是怎样产生的呢？

本人对您们的中文细粒度实体分类研究很感兴趣，期待您的回复，谢谢!
另您论文中的邮箱联系不上，可以给个新的邮件地址吗？

Yours,
Pan Liu
刘盼

下载链接已经失效了，可以更新一下吗？

下载不了