issues
search
makcedward
/
nlpaug
Data augmentation for NLP
https://makcedward.github.io/
MIT License
4.46k
stars
463
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
Fix script indentation
#348
sbrugman
opened
2 months ago
0
Added the Persian mapping
#347
Keramatfar
opened
5 months ago
0
Using nas.ContextualWordEmbsForSentenceAug with gpt2 or distilgpt2 returns nonsense
#346
djaszak
opened
6 months ago
0
Is support for facebook/bart-base removed in the latest version?
#345
imranraad07
opened
7 months ago
0
Not able to presever the words.
#344
Opperessor
opened
8 months ago
0
Feature Request: Progress bar during augmentation
#343
bauersimon
opened
9 months ago
0
instancing more than one naw spelling aug with diferent dict_path doesn't work
#342
jhpiedrahitao
opened
1 year ago
0
Bug on 1.1.11
#340
ririya
opened
1 year ago
0
Error with English to French Backtranslation
#339
alejopaullier96
opened
1 year ago
0
Actively maintained?
#338
Ubadub
opened
1 year ago
3
TypeError when utilizing GPU on Apple silicon for language models
#337
BlueJ1
closed
1 year ago
0
Augmenting Long Documents
#336
vc34
opened
1 year ago
0
The tokenizer class you load from this checkpoint is 'RobertaTokenizer'
#335
bhomass
opened
1 year ago
0
does `ContextualWordEmbsAug` support XLM-Roberta models
#334
cmgchess
opened
1 year ago
1
What is the correct way to specify include_detail=True?
#333
chanind
opened
1 year ago
0
LookupError when trying to augment data with SynonymAug
#332
moonman239
opened
1 year ago
0
Removed 'num_workers' parameter as it gives error while running the lambada model
#331
Onkar-2803
opened
1 year ago
0
RuntimeError: DataLoader worker (pid(s) 3954) exited unexpectedly
#330
pratikchhapolika
opened
1 year ago
0
Short description about different parameters used inside augmenter and what it does?
#329
pratikchhapolika
opened
1 year ago
0
Lambada Model giving gibberish output
#328
Onkar-2803
opened
1 year ago
0
Unable to generate new data
#327
yuchen74
opened
1 year ago
0
lambada augmenter: The following `model_kwargs` are not used by the model: ['num_workers']
#326
NhatHoang2002
opened
1 year ago
2
ContextualWordEmbsAug: extra whitespace before and after punctuaion
#325
MT010104
opened
1 year ago
0
Remove invalid num_beam argument from textual_augmenter
#324
barseghyanartur
opened
1 year ago
0
Question: Is there an (easy) way to preserve (trailing) spaces and carriage returns when using `ContextualWordEmbsAug`?
#323
barseghyanartur
opened
1 year ago
0
load_word2vec_format() got an unexpected keyword argument 'no_header'
#322
Hossein-1991
opened
1 year ago
0
Fix typos
#321
tshu-w
opened
1 year ago
0
Numpy Error
#320
akhileshrai003
opened
1 year ago
0
Coverage of "Data Augmentation using Pre-trained Transformer Models" paper in this library
#319
kumar-abhishek
opened
1 year ago
0
Muti-gpu support
#318
slvcsl
opened
1 year ago
0
Typeerror with ContextualWordEmbsAug
#317
zhangyaqi20
opened
1 year ago
1
Can't extract `str` to `Vec` while using nas.ContextualWordEmbsForSentenceAug(model_path='xlnet-base-cased')
#316
EtherealRise
opened
1 year ago
2
`candidates` in `RandomCharAug` is not working as expected
#315
lindsaydbrin
opened
2 years ago
0
Add check to fix bug caused by short token lists in word augmenter
#314
rohit-gupta
opened
2 years ago
0
Character Augmenters remove non-breaking spaces before punctuation and insert spaces around apostrophes
#313
lindsaydbrin
opened
2 years ago
3
Duplicate lines in example
#312
ziqing-huang
opened
2 years ago
0
In the documentation it is unclear about the spelling dictionary
#311
xihajun
closed
2 years ago
2
UnknownExtra: requests 2.27.1 has no such extra feature 'socks'
#310
moe-men
opened
2 years ago
1
Process finished with exit code 132 (interrupted by signal 4: SIGILL)
#309
alaa-maverick
opened
2 years ago
0
UnicodeDecodeError: 'utf-8' codec can't decode byte 0x80 in position 0: invalid start byte
#308
NitishOritro
opened
2 years ago
0
AbstSummAug doesn't have num_beam parameter
#307
Oleg-Litvinov-EPAM
opened
2 years ago
0
Release 1.1.11
#306
makcedward
closed
2 years ago
0
allow to use word embeddings models with different formats
#305
IgorMunizS
opened
2 years ago
1
Truncate to model max length in back translation
#304
JohnGiorgi
closed
2 years ago
0
Change WordAugmenter clean type-checking to catch all list-comprehens…
#303
sami-bg
closed
2 years ago
0
Consistent data type (list) for char augmenters
#302
fratambot
closed
2 years ago
1
Util for downloading from Google Drive no longer works
#301
MarkusSagen
closed
2 years ago
0
Fix util script for downloading Google Drive files and Word2Vec weights
#300
MarkusSagen
closed
2 years ago
0
Using Offline models
#299
chechu-arias
closed
2 years ago
1
Fix typos in back_translation module
#298
JohnGiorgi
closed
2 years ago
0
Next