LatticeLSTM

LatticeLSTM copied to clipboard

Hi jiesutd, I've got ontonotes-4.0 copyright from LDC, and tryed to split the NER data set by myself. But I've got a different size of data set, especially on dev...

GaoYb923

About training time

3

大家好呀，有没有人知道run demo之后要训练多久才能出结果呢？

XY2323819551

数据怎么换成自己的数据集呢

cc846049716

训练起来非常的慢，我发现主要是因为batch_size在main.py中被设置为1了，而且改了这个参数后，会在model/latticelstm.py：142行提醒报错，初步猜想是作者并没有进行batch_size的其他值的调试，或许会导致一些其他的bug产生。哪位大佬有空能够修正下batch_size的问题吗？

hrshy0629

RuntimeError: set_storage is not allowed on a Tensor created from .data or .detach().

4

```python weight_hh_data = torch.eye(self.hidden_size) weight_hh_data = weight_hh_data.repeat(1, 3) self.weight_hh.data.set_(weight_hh_data) alpha_weight_hh_data = torch.eye(self.hidden_size) alpha_weight_hh_data = alpha_weight_hh_data.repeat(1, 1) self.alpha_weight_hh.data.set_(alpha_weight_hh_data) ``` > model\latticelstm.py", line 107, in reset_parameters > self.weight_hh.data.set_(weight_hh_data) > RuntimeError: set_storage is...

actforjason

```python i, o, g = torch.split(wh_b + wi, split_size_or_sections=self.hidden_size, dim=1) i = torch.sigmoid(i) g = torch.tanh(g) o = torch.sigmoid(o) c_num = len(c_input) if c_num == 0: f = 1 -...

actforjason

where is segmentation label embedding lookup table?

1

你好，我想问一下Character-Based Model部分 Char+softword中segmentation label embedding lookup table这个表用的是什么文件呢？

zhangfeiyu5610

您好，请问您可以分享一下ontonote4.0的数据集么，我的邮箱是[email protected]，我可以先把授权发给您。

tyistyler

when i run test/decode, there is an error on "load_model_decode". Information like: _size mismatch for lstm.hidden2tag.weight: copying a param with shape torch.Size([20, 200]) from checkpoint, the shape in current model...

jjj9china

您好！我想请问下ner任务上在构建char2id的字典映射时，这个除了使用训练集的语料构建，是否可以额外补充预训练char向量中的char到上面的char2id里面？正确的构建方法是什么呢？

topDreamer