conv_relation icon indicating copy to clipboard operation
conv_relation copied to clipboard

TensorFlow implementation of Relation Classification via Convolutional Deep Neural Network

Results 8 conv_relation issues
Sort by recently updated
recently updated
newest added

为什么把 lexical reshape 成 6×word_dim?6的含义是什么?

In the paper, it says: ![image](https://user-images.githubusercontent.com/18495787/49399919-a7b51500-f710-11e8-875e-4b540fcb223c.png) The position should be calculated for each word in the sentence, relative to the two target entity words. An example was given in the...

您好,请问data文件夹下“.cln”结尾的数据集中前五个数字表示什么?是词级别特征中的五个特征么?为什么是数字? 是否有数据预处理的代码? 谢谢

能提供一下原始的数据集吗?

Hello Frank, @FrankWork I think you have implemented the model well. However, it seems you have made a mistake because you use test dataset as the validation dataset (which is...

您好!我想知道您是否将您的模型修改为PCNN,是否有公开的源码。

Hi, Thanks for your released code. I have run the code and got the Accuracy is **0.779** and no F1-score(In fact the **F1-score** will be smaller about 4-5% than the...

According [scorer.pl](https://github.com/vzhong/semeval/tree/master/dataset/SemEval2010_task8_scorer-v1.2), they said > In the examples above, the first three files are OK, while the last one contains four errors. And answer_key2.txt contains the true labels for the...