|
What are some popular datasets for domain adaptation in NLP
|
|
1
|
470
|
November 12, 2020
|
|
Attention and hidden state details from t5
|
|
0
|
193
|
November 12, 2020
|
|
Gradient accumulation averages over gradient
|
|
2
|
2000
|
November 12, 2020
|
|
Clarification: finetune.py max target length
|
|
2
|
442
|
November 12, 2020
|
|
Transformers v4.0.0 announcement
|
|
2
|
2242
|
November 12, 2020
|
|
GPT 2.5-open source
|
|
2
|
554
|
November 12, 2020
|
|
Simple trick to make any architectures handle multiple languages - XLM-X
|
|
0
|
273
|
November 13, 2020
|
|
I meet the zero gradient descent
|
|
7
|
886
|
November 13, 2020
|
|
DPR retriever module
|
|
1
|
831
|
November 6, 2020
|
|
AutoModelForQuestionAnswering : TypeError: __init__() got an unexpected keyword argument 'return_dict'
|
|
2
|
2420
|
November 13, 2020
|
|
Finetuning T5 on custom data
|
|
0
|
1056
|
November 13, 2020
|
|
Custom DistilBertTokenizer training
|
|
3
|
653
|
November 13, 2020
|
|
Distributed Training on Databricks
|
|
0
|
895
|
November 14, 2020
|
|
GPT2 with TensorFlow?
|
|
1
|
370
|
November 14, 2020
|
|
Stop generation while using past in GPT-2
|
|
0
|
1082
|
November 15, 2020
|
|
Cannot download wmt16
|
|
0
|
431
|
November 16, 2020
|
|
Special tokens and inference
|
|
0
|
333
|
November 16, 2020
|
|
New Model sharing and uploading is extremely slow
|
|
2
|
3535
|
November 16, 2020
|
|
Learning rate setting
|
|
1
|
1943
|
November 16, 2020
|
|
Evaluation metrics
|
|
1
|
1998
|
November 16, 2020
|
|
The reason `prepare_seq2seq_batch` for ProphetNet is not existed
|
|
11
|
869
|
November 16, 2020
|
|
Issue with tokenizer.tokenize
|
|
3
|
503
|
November 16, 2020
|
|
Multiple-Token Input for Text Generations and PPLM?
|
|
13
|
2495
|
November 16, 2020
|
|
Abbreviation expansions
|
|
0
|
731
|
November 17, 2020
|
|
mBART finetuning tips/post-mortem
|
|
6
|
2619
|
November 17, 2020
|
|
Convert mT5 to HF weights?
|
|
6
|
991
|
November 17, 2020
|
|
Multilingual T5 Model Not Found?
|
|
3
|
1123
|
November 17, 2020
|
|
Finding gradients in zero-shot learning
|
|
4
|
2824
|
November 17, 2020
|
|
Funcom Dataset for summarization
|
|
2
|
564
|
November 17, 2020
|
|
Specify attention masks for some heads in multi-head attention
|
|
3
|
2319
|
November 17, 2020
|