|
Any ways to visualize attention of the LXMERT?
|
|
0
|
15
|
April 17, 2021
|
|
Masked Language Model Scoring
|
|
3
|
27
|
April 16, 2021
|
|
Human Evaluation and Statistical significance
|
|
0
|
30
|
April 8, 2021
|
|
Copying mechanism for transformer
|
|
1
|
87
|
March 30, 2021
|
|
ASR spell correction
|
|
20
|
345
|
March 26, 2021
|
|
Any study of failures of nlp models vs schoolchildren on QA or POS?
|
|
0
|
41
|
March 24, 2021
|
|
`nan` training loss but eval loss does improve over time
|
|
4
|
182
|
March 23, 2021
|
|
How to instill auxiliary information coupled with words into transformers?
|
|
0
|
36
|
March 19, 2021
|
|
Zero-shot and distillation - Improved distilled model over teacher model
|
|
0
|
65
|
March 18, 2021
|
|
XLSR-53: To group tokens or not to group tokens
|
|
1
|
53
|
March 18, 2021
|
|
Online/streaming speech recognition
|
|
0
|
73
|
March 17, 2021
|
|
NER for 2D text
|
|
0
|
46
|
March 16, 2021
|
|
Dealing with Imbalanced Datasets?
|
|
1
|
64
|
March 11, 2021
|
|
How does BERT actually answer questions?
|
|
1
|
70
|
March 11, 2021
|
|
Hugging Face Reads - 01/2021 - Sparsity and Pruning
|
|
13
|
2784
|
March 8, 2021
|
|
Guide: The best way to calculate the perplexity of fixed-length models
|
|
5
|
604
|
March 1, 2021
|
|
FDA Label Document Embedding
|
|
9
|
113
|
February 19, 2021
|
|
Likelyhood input sequence came from training set
|
|
0
|
45
|
February 17, 2021
|
|
Why are embedding / pooler layers excluded from pruning comparisons?
|
|
7
|
77
|
February 16, 2021
|
|
Debugging the RAG question encoder
|
|
2
|
83
|
February 10, 2021
|
|
Question about maximum number of tokens
|
|
1
|
74
|
February 9, 2021
|
|
Science Tuesday: MARGE
|
|
7
|
1640
|
February 8, 2021
|
|
RAG for FEVER Dataset
|
|
0
|
51
|
February 8, 2021
|
|
Transfer learning to explore tasks' information requirements?
|
|
0
|
53
|
February 5, 2021
|
|
Model or Dataset available for classifying a grammatical sentence?
|
|
1
|
65
|
February 3, 2021
|
|
Generating coherent related text with generative model (GPT2 etc.)
|
|
0
|
58
|
January 28, 2021
|
|
RoBERTa trained on NSP
|
|
0
|
60
|
January 12, 2021
|
|
Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity
|
|
1
|
182
|
January 20, 2021
|
|
Significance of the [CLS] token
|
|
4
|
179
|
January 18, 2021
|
|
The (hidden) meaning behind the embedding of the padding token?
|
|
0
|
86
|
January 15, 2021
|
