nju-websoft / contea Goto Github PK

Hello,

Thanks for sharing the code and datasets. They are very helpful.
I've discovered that there are some pairs in the original ground-truth are missing in your training, validation, and testing pairs.

For example, both 19156 and 34323 do not appear in

• ContEA/datasets/FR-EN/base/train_links
• ContEA/datasets/FR-EN/base/valid_links
• ContEA/datasets/FR-EN/base/test_links

While they do appear in ContEA/datasets/FR-EN/ent _dict file as

• 19156: http://fr.dbpedia.org/resource/Université_Lille_I
• 34323: http://dbpedia.org/resource/Lille_University_of_Science_and_Technology

And the pair ("http://fr.dbpedia.org/resource/Université_Lille_I", "http://dbpedia.org/resource/Lille_University_of_Science_and_Technology") does exist in the original ground-truth.

There are 329 such pairs for FR-EN dataset.
Could you please double check? Thanks!

作者你好，拜读过你的论文后，我对你的研究十分感兴趣。但是我有个疑问，在你的实验设置中采用了Precision、Recall、F1指标评估模型性能，但是有好多实体对齐模型采用了Hit@k、MRR指标来评估模型性能。请问这两种评估体系有什么区别，还有就是两种评价指标是否存在一定的转换关系，比如Hit@1和Precision是否有一定的转换关系。

Hello, when running the ZH-EN dataset, I encountered the following error. How can I fix it?

运行后后出现如下问题，我的服务器内存有32G 不够用吗？
terminate called after throwing an instance of 'std::bad_alloc'
what(): std::bad_alloc
run.sh: line 17: 8933 Aborted (core dumped) python main.py --batch 'base' --gpu ${g} --dataset ${ds} --batch_size 1024 --lr 0.0005 --alpha 0.01 --beta ${beta} --save_path ${saved_path} --log_path ${log_path} --stop_step 3 --M ${M}
run.sh: line 17: 8948 Segmentation fault (core dumped) python main.py --batch 'batch1' --load_path ${baseModel} --gpu ${g} --dataset ${ds} --batch_size 512 --lr 0.01 --save_path ${saved_path} --log_path ${log_path} --alpha ${alpha} --beta ${beta} --M ${M}
terminate called after throwing an instance of 'std::bad_alloc'
what(): std::bad_alloc
run.sh: line 48: 8956 Aborted (core dumped) python main.py --batch "batch${b}" --load_path ${lastModel} --gpu ${g} --save_path ${saved_path} --log_path ${log_path} --dataset ${ds} --alpha ${alpha} --beta ${beta} --M ${M}
terminate called after throwing an instance of 'std::bad_alloc'
what(): std::bad_alloc
run.sh: line 48: 8970 Aborted (core dumped) python main.py --batch "batch${b}" --load_path ${lastModel} --gpu ${g} --save_path ${saved_path} --log_path ${log_path} --dataset ${ds} --alpha ${alpha} --beta ${beta} --M ${M}
terminate called after throwing an instance of 'std::bad_alloc'
what(): std::bad_alloc
run.sh: line 48: 8979 Aborted (core dumped) python main.py --batch "batch${b}" --load_path ${lastModel} --gpu ${g} --save_path ${saved_path} --log_path ${log_path} --dataset ${ds} --alpha ${alpha} --beta ${beta} --M ${M}
terminate called after throwing an instance of 'std::bad_alloc'
what(): std::bad_alloc
run.sh: line 48: 8993 Aborted (core dumped) python main.py --batch "batch${b}" --load_path ${lastModel} --gpu ${g} --save_path ${saved_path} --log_path ${log_path} --dataset ${ds} --alpha ${alpha} --beta ${beta} --M ${M}

hi,my friend, would you like to share your paper and code about this github ?
https://audreyw.top/AboutMe/projects/2_project/

作者您好，

 读了您的论文，我对您的研究非常感兴趣。但是对论文中t大于0的数据集构建(section 4.1)有一些疑问，没有看明白。

 文中说，t大于0时，先从DBpedia中搜集包含KGt-1中实体的关系三元组。然后删除KGt-1中存在的关系三元组。

 下面这段话，我理解上有一些问题感觉。
 接着从DBpedia中剩余的三元组中采样KGt-1中20%量的新三元组？将这些新三元组添加到KGt-1中，然后创建KG1t和KG2t。

我对这里的流程还是不太明白，麻烦作者能给详细介绍一下吗？非常感激您！

Hi,my friends, i want to know how to get results of your baselines(eg:DINGAL-O) in your paper? Could you share the code of baselines about this task? Thank you very much.