lanzhuzhu

hi, 我也看了这篇论文，想请教一下，在监督的关系分类模型上，即图2左的模型是怎么学习到每个类的表示的呢？是用一个矩阵表示，和transformer+linear之后的输出向量 相乘然后softmax分类，根据loss优化这个矩阵得到的吗？这样似乎并不能保证这个矩阵能优化成类的表示呢？

I met the same problem. I used the embedding "glove.6B.300d.txt" and tested the two versions of your code. One model is "chars_lstm_lstm_crf model ", the other is "sequence_tagging". From my...

> Hi, the clean validation set is split from the training set. Thanks a lot for your reply!