-
when I run this code,I find the code" optimizer = dc.hyper.HyperparamOpt(model_builder)" was a traceback.the error is 'HyperparamOpt is an abstract superclass and cannot be directly instantiated. …
-
**Issue by [antgr](https://github.com/antgr)**
_Sunday Nov 17, 2019 at 15:07 GMT_
_Originally opened as https://github.com/nyu-mll/jiant/issues/962_
----
Hi,
I would like to apply multitask learni…
-
### Description
Combining multi task learning with Squad fails because of different data structures.
### Traceback
```
"Incompatible return values of true_fn and false_fn: {}".format(e))
Valu…
-
### Metadata
- Authors: Marek Rei
- Organization: University of Cambridge
- Conference: ACL 2017
- Link: https://goo.gl/h6p29c
-
In this tutorial, what is the purpose of swapping the valid_dataset and the test_dataset after train-test split?
```
splitter = dc.splits.RandomSplitter(dataset_file)
train_dataset, valid_dataset…
-
I tried this example and i change the scoring metrics to kappa score instead of ROC-AUC score in the example.
```
metric = dc.metrics.Metric(dc.metrics.kappa_score, np.mean)
optimizer = dc.hyper.…
-
**Is your feature request related to a problem? Please describe.**
How do I return multiple labels for multitask learning?
I want to train a multitask regression network as shown below.
**Describ…
-
### Describe the bug
Thank you for developing and maintaining this invaluable module!
We would like to learn a multi-task model on two NER tasks by sharing a transformer word embedding.
We fine-t…
-
I'm using (and have used successfully in the past) a Multitask GP in GPyTorch to model sets of 2-d data. However, in many instances, I notice that the covariance factor array does not move away from t…
-
## 一言でいうと
自然言語処理のタスク全10個を単一のモデルで解く新しい問題設定と評価手法の提案。タスクは要約・翻訳・質問回答など様々なものを含むが、フォーマットは質問回答の形に還元されている(要約なら、「この文の要約は？」になるなど)。マルチタスクで学習を行い、転移性能が確認できたとのこと。
![image](https://user-images.githubuserconten…