|
Improving performance of Wav2Vec2 fine tuning with word piece vocabulary
|
|
4
|
177
|
July 30, 2021
|
|
Text similarity not by cosine similarity
|
|
1
|
32
|
July 29, 2021
|
|
Best way to infer continuously with Transformer?
|
|
0
|
24
|
July 26, 2021
|
|
Guide: The best way to calculate the perplexity of fixed-length models
|
|
6
|
1023
|
July 15, 2021
|
|
The (hidden) meaning behind the embedding of the padding token?
|
|
2
|
357
|
July 14, 2021
|
|
Language model to search an answer in a huge collection of (unrelated) paragraphs
|
|
4
|
182
|
July 6, 2021
|
|
Address extraction and formated using Places API (Google Maps API)
|
|
0
|
48
|
July 4, 2021
|
|
Fine tuning gpt-neo via ppo
|
|
0
|
44
|
July 2, 2021
|
|
LayoutLM for extraction of information from tables
|
|
0
|
27
|
June 27, 2021
|
|
Seq2Seq Distillation: Methodology Questions
|
|
5
|
513
|
June 25, 2021
|
|
Finetuning for fp16 compatibility
|
|
2
|
198
|
June 17, 2021
|
|
What can transformers learn without position encoding?
|
|
1
|
109
|
June 10, 2021
|
|
Extracting Training Data from GPT-2 (+ Differential Privacy)
|
|
0
|
55
|
June 6, 2021
|
|
Copying mechanism for transformer
|
|
2
|
382
|
June 2, 2021
|
|
Project Description
|
|
1
|
53
|
May 29, 2021
|
|
Does it make sense to generate sentences with Transofmrer's encoder?
|
|
0
|
61
|
May 22, 2021
|
|
PEGASUS model overfitting
|
|
2
|
73
|
May 19, 2021
|
|
ELECTRA training reimplementation and discussion
|
|
10
|
2532
|
May 13, 2021
|
|
Classification Heads in BERT and DistilBERT for Sequence Classification
|
|
2
|
98
|
May 13, 2021
|
|
Collaborative Training Experiment of an Albert Model for Bengali
|
|
1
|
630
|
May 6, 2021
|
|
Multi-GPU Machine Setup Guide and QnA
|
|
6
|
416
|
May 1, 2021
|
|
XLSR-Wav2Vec2 with punctuation
|
|
0
|
142
|
April 26, 2021
|
|
Task-specific fine-tuning of GPT2
|
|
0
|
94
|
April 22, 2021
|
|
Is causal language modeling (CLM) vs masked language modeling (MLM) a common distinction in NLP research?
|
|
0
|
216
|
April 21, 2021
|
|
Any ways to visualize attention of the LXMERT?
|
|
0
|
96
|
April 17, 2021
|
|
Masked Language Model Scoring
|
|
3
|
160
|
April 16, 2021
|
|
Human Evaluation and Statistical significance
|
|
0
|
92
|
April 8, 2021
|
|
ASR spell correction
|
|
20
|
604
|
March 26, 2021
|
|
Any study of failures of nlp models vs schoolchildren on QA or POS?
|
|
0
|
88
|
March 24, 2021
|
|
`nan` training loss but eval loss does improve over time
|
|
4
|
334
|
March 23, 2021
|
