-
Hi,
I want to use the output variable which stores the aspect, sentiment pairs of the input sentence. I think it is the **output_ts** variable in work.py
I actually want to use it in a different…
ghost updated
3 years ago
-
## 🐛 Bug
I am using `nn.DataParallel` for a Neural Machine Translation task, when the number of parallel sentences is more than 10 millions, the training speed becomes much slower. After some analy…
ghrua updated
4 years ago
-
Hi all, thanks for the resource. I'm interested in using this dataset, but I am finding the EDP test data to be quite misaligned. My script which extracts segments from the bioC files show:
```log
…
-
Hello，I reproduce this paper with the dataset in WMT. Then I got:
Training: Loss = 0.000887, Accuracy = 0.9981, Precision = 0.9998, Recall = 0.9889, F1 = 0.9943
Validing: Loss = 0.003075, Accur…
-
The following papers appear to have a lot of overlap with the goals that we are trying to accomplish with this project. They could offer some good insights into how we could improve the current proces…
-
Trying to reproduce the correlations obtained in the paper (recomputing actual metric scores) for BLEU, I noticed some strange values in the file with BLEU scores at the segment level. There are pairs…
-
A common use case with multimodal models is having extended text captions to go with images. For example, the dataset may be curated by scraping a google images search and storing `(caption, title of …
-
Hi ,
I want to translate a string ending with full Stop, But It is unable to translate.
eg:
My Key Value Pairs
[{ :"Requested part is not available in your on site FSL."=>
"Parte richiesta non è di…
-
https://arxiv.org/abs/1704.03470
참고) https://github.com/chullhwan-song/Reading-Paper/issues/26 이논문 이후의 연구임.
-
In the make_del_knob function, when the size product (e_size * f_size) is smaller than the sample_size (20000 by default), the script ends up calculating the similarity score for all combinations of t…