|
[Suggestions and Guidance]Finetuning Bert models for Next word Prediction
|
|
1
|
15
|
January 24, 2022
|
|
Paper Notes: Deepspeed Mixture of Experts
|
|
2
|
144
|
January 20, 2022
|
|
Using mixup on RoBERTa
|
|
6
|
656
|
July 21, 2020
|
|
How does the vocabulary size count towards total parameter size of a model?
|
|
0
|
48
|
January 18, 2022
|
|
Feeding a Knowledge Base into Transformer model
|
|
0
|
90
|
December 27, 2021
|
|
ASR spell correction
|
|
25
|
1690
|
December 17, 2021
|
|
Copying mechanism for transformer
|
|
5
|
1245
|
December 16, 2021
|
|
Guide: The best way to calculate the perplexity of fixed-length models
|
|
9
|
2147
|
December 16, 2021
|
|
Generating Synthetic Data for Machine Translation of Dialects
|
|
0
|
113
|
December 13, 2021
|
|
Few shot automatic moderation
|
|
0
|
156
|
November 20, 2021
|
|
Let's Make an Ethics Chat Bot that's Not Racist!
|
|
0
|
163
|
November 16, 2021
|
|
New Paper: Masked Autoencoders Are Scalable Vision Learners
|
|
0
|
395
|
November 14, 2021
|
|
Text similarity not by cosine similarity
|
|
2
|
627
|
October 29, 2021
|
|
Improving performance of Wav2Vec2 fine tuning with word piece vocabulary
|
|
5
|
813
|
October 27, 2021
|
|
[Help needed] Extending Trainer for Meta learning
|
|
3
|
589
|
October 19, 2021
|
|
Why are huge batch sizes used for pretraining and small ones for finetuning?
|
|
1
|
329
|
October 18, 2021
|
|
ELECTRA training reimplementation and discussion
|
|
12
|
3444
|
October 16, 2021
|
|
Call for Participation: SemEval 2022 Task 2 Multilingual Idiomaticity Detection and Sentence Embedding
|
|
0
|
185
|
October 4, 2021
|
|
Detection Transformer (DETR) for text detection in documents
|
|
0
|
276
|
September 29, 2021
|
|
Using NLP for People On Low Income in the UK
|
|
0
|
210
|
September 24, 2021
|
|
Summarization for downstream task
|
|
0
|
203
|
September 15, 2021
|
|
Online/streaming speech recognition
|
|
1
|
521
|
September 11, 2021
|
|
Significance of the [CLS] token
|
|
12
|
1982
|
September 9, 2021
|
|
[Call for participation] Interactive Grounded Language Understanding in a Collaborative Environment (IGLU) Competition@NeurIPS2021
|
|
0
|
201
|
September 9, 2021
|
|
Implementing a custom Attention Transformer
|
|
5
|
382
|
September 6, 2021
|
|
Collaborative Training Experiment Round 2 with Yandex and HuggingFace
|
|
0
|
255
|
September 1, 2021
|
|
Tutorial / codebase for models interacting while training?
|
|
0
|
191
|
August 29, 2021
|
|
Citing/Crediting Language Models
|
|
2
|
441
|
August 2, 2021
|
|
10_000 samples & 10_000 labels
|
|
0
|
217
|
July 31, 2021
|
|
Best way to infer continuously with Transformer?
|
|
0
|
282
|
July 26, 2021
|
