|
Bart-base rouge scores
|
|
3
|
40
|
August 14, 2020
|
|
Science Tuesday: MARGE
|
|
7
|
324
|
August 14, 2020
|
|
Meta learning example
|
|
1
|
34
|
August 8, 2020
|
|
Carrying Gradients Through Generate
|
|
4
|
65
|
August 6, 2020
|
|
BART question, it seems that pretraining is not work for a small model?
|
|
7
|
67
|
August 3, 2020
|
|
Why are segment and position embeddings so large?
|
|
3
|
146
|
August 2, 2020
|
|
Understanding what went wrong in attention
|
|
6
|
139
|
July 31, 2020
|
|
ACL 2020 highlights – Joe
|
|
4
|
502
|
July 30, 2020
|
|
Finetuning German BERT for QA on biomedical domain
|
|
2
|
28
|
July 28, 2020
|
|
Debiasing models by HEX projection
|
|
2
|
33
|
July 28, 2020
|
|
What does it mean to prime a GPT model?
|
|
6
|
150
|
July 27, 2020
|
|
Attaching TF models to CNN features
|
|
2
|
46
|
July 24, 2020
|
|
Is it reasonableto pretrain by masking certain dimensions of each vector, rather than the individual token?
|
|
4
|
60
|
July 21, 2020
|
|
Using mixup on RoBERTa
|
|
7
|
99
|
July 21, 2020
|
|
Print All Tokens Over a Certain Probability Threshold
|
|
4
|
60
|
July 21, 2020
|
|
Building a custom Squad 2.0 style dataset, is it worth it?
|
|
4
|
39
|
July 20, 2020
|
|
State of the art technique for initializing Embedding Matrix?
|
|
4
|
70
|
July 19, 2020
|
|
Modern NLP for "Economics of Innovation" (Open Research Project using Patent Data)
|
|
5
|
115
|
July 14, 2020
|
|
ACL 2020 - Some personal highlights - Victor
|
|
5
|
391
|
July 14, 2020
|
|
ICLR 2020 highlights - Yacine
|
|
2
|
586
|
July 11, 2020
|
|
About the Research category
|
|
3
|
66
|
July 11, 2020
|
|
Guide: The best way to calculate the perplexity of fixed-length models
|
|
1
|
218
|
July 10, 2020
|
|
ACL 2020 highlights – Canwen
|
|
2
|
343
|
July 10, 2020
|
|
ACL 2020 highlights - Yacine
|
|
1
|
285
|
July 10, 2020
|
|
Paper Discussion: Weight Poisoning Attacks on Pre-trained Models
|
|
1
|
74
|
July 8, 2020
|
