-
**Issue by [sleepinyourhat](https://github.com/sleepinyourhat)**
_Thursday Jun 28, 2018 at 21:36 GMT_
_Originally opened as https://github.com/nyu-mll/jiant/issues/64_
----
Not top priority, but th…
-
**Describe the bug**
Non-deterministic output from the ELMo embedding
**To Reproduce**
Following this tutorial
https://github.com/allenai/allennlp/blob/master/tutorials/how_to/elmo.md#using-elmo…
-
Hi. Thank you for sharing your code. It make a great help and I learnt a lot from it.
I'm a little confused about the **padding_idx = 1** in self.char_emb. In my opinion, this para means that whe…
-
**System (please complete the following information):**
- OS: Linux
- Python version: 3.6.
- AllenNLP version: "I installed from master"
- PyTorch version: 1.1
**Question**
Ask about some…
-
您好，想请问可以用CharCNN+CRF或者是只用CRF吗？
非常感谢回答~
-
Character-level convolutional networks require a lot of data to train on (based on my experience using the model for document classification). This is not something we currently possess. Further, our …
-
hi,
Why you set the input layer size equal to 1014 and in your another code repository CharCnn_Keras, you
put a config.json file, is that a config file of caffee or torch? thanks.
-
Hi,
My name is Alex Haigh, and I'm a master's student at Stanford. For a project, I'm working to reproduce (and hopefully extend) some of your results on VarNaming from your '18 ICLR paper. My u…
-
There're a lot of classification models for sentences like CharCNN/RNN, VDCNN, etc...
Implement/Test at least 3 classification models.
- [x] CharCNN
- [x] CharRNN
-
Hi,
I am trying to run CharCNN on 4 GeForce GTX 1080.I am struggling with 2 problems.
1. The 4 GPUs seem to have unbalanced load.When I ran `nvidia-smi`,the result is shown as following
![image](ht…