-
Hi,
I am trying to reproduce the experiments but I can't find which distance metric is used to construct the dissimilarity matrices. Would you be so kind to provide the code or tell me which metric…
-
I'm preparing a benchmark of selected LM's available in Flair in sentence classification task on TREC6. To my surprise 10-fold-cross validated results of training a sentence-classifier with exactly th…
-
Hello,
I read your paper. I hope it will be accepted. I have some suggestions to improve your paper or give you some ideas for future work.
1. You had faced with imbalanced datasets and used under…
-
Hey everyone.
Im trying to understand the differences in using several word embeddings (BERT, XLM, ..) with this framework and using the embeddings in other framework, e.g. huggingface
To be more…
-
Many ML tasks require require optimization wrt a different objective than the least squares and cross-entropy defined already. Hence, for our supervised learning to be useful in the real world, we nee…
-
Most datasets are unbalanced (different sizes of positive and negative samples); Although F1 score is usually considered as metric; however, it needs to be careful to assign positive samples. If assig…
-
**Describe the bug**
Currently, the tests take around 600s. But only a few tests take the majority of this time. The short term solution is to make those specific tests shorter, the long term solut…
-
Describe the additional metrics in subsections of Section 3 (Methods):
Deterministic metrics, with subsubsections for:
- [ ] ~~Accuracy~~
- [ ] F1 score @mi-dai
- [ ] ~~Matthews Correlation Coe…
-
-
**Describe the bug**
Training data is [twitter airline sentiment](https://www.kaggle.com/crowdflower/twitter-airline-sentiment).
My model definition yaml is
```
input_features:
-
na…