-
Hi,
It seems that some of the prediction files truncate sentences too short. For example, here is a long sentence in Hausa in the test file:
* https://github.com/masakhane-io/masakhane-ner/blob/ma…
-
Hi
I am trying to generate negations out of non-negated sentences.
I used a simple “I have tea” => “I don’t have tea” formatted dataset for training an XLMR encoder-decoder model using the example p…
-
Could you please provide an example of XNLI tasks for XLM-RoBERTa?
Current example (https://github.com/pytorch/fairseq/tree/master/examples/xlmr) is quite simple and it is for single sentence.
Thank…
-
Tensorflow 2.0 RC on Colab can not work. @yuefengz
```python
cluster_resolver = tf.distribute.cluster_resolver.TPUClusterResolver(tpu='grpc://' + os.environ['COLAB_TPU_ADDR'])
tf.config.experimen…
-
I run into this error when training a model with encoder=bert on the Italian UD training set:
python -u -m supar.cmds.biaffine_dep train -p=exp/it_isdt.dbmdz-electra-xxl/model \
-c=config.ini -…
-
Yep, that's what the [classification heads](https://github.com/pytorch/fairseq/blob/master/fairseq/models/roberta/model.py#L273) do
_Originally posted by @lematt1991 in https://github.com/pytorch/f…
-
When training with a batch size of 32 (grad accummulation step = 1), training speed is approximately 6 it/s, however I increase gradient accummulation step to 4 or 8 (equivalent to batch size of 128 a…
-
Hi:
Good evening!
I read from your paper that Unicode uses an XLM/transformer structure.
…
-
**Describe the feature and the current behavior/state.**
I've been looking into hanlp source code and documentation to find a way to get the index of a token or a ner in the original input text. …
-
Hi, I'm Interested in your great work and tried to reproduce you results of fine-tuning XLMR (with my own code). And I got `92.6` in `Ritter11`, `93.4` in `ARK`, `95.0` in `TB-v2`. I find that the re…