Welcome to
mirror list
, hosted at
ThFree Co
, Russian Federation.
github.com/stanfordnlp/stanza.git - Unnamed repository; edit this file 'description' to name the repository.
index
:
github.com/stanfordnlp/stanza.git
142_resources_patch
NFC
am-notes
aws_sagemaker_tooling
azshan
beam
bert_mix
charlm_cache
charlm_checkpoint
con_add_pattn
con_attn2
con_bigrams
con_checkpoint
con_classifier
con_classifier_reranking
con_focal
con_freeze
con_kbest
con_lattn
con_lattn2
con_mixed_pattn
con_mlp
con_mlp_inputs
con_multitask
con_pattn_lr
con_pattn_replace
con_restart_transitions
con_self_gan
con_shift_tags
con_shift_tags2
con_shift_transitions
con_simple_transformer
con_simple_unary
con_skip
con_trans
con_tree_lstm
con_tree_lstm2
con_tree_lstm3
con_tstack
con_vector_dropout
con_vit
con_warmup
con_warmup_2
con_warmup_lattn
dataloader_local
de_ner
dev
elmo2
elmo_many
fewer_cuda
fix_unit_tests
gh-pages
gh-pages-sent
hebrew_combined
hi-layered-ner
hi-ner-cleaned
hi-shuffle
hi_ner
hi_ner_final
inorder_unary
kazakh_ner
kk_trans
lattn_issue
m1
main
marathi
margin_penalty
masakhane
masks
masks2
masks3
ner_bert
ner_bert_copy
ner_wv
ninf_langid
nner
no_header_pt
numeric_re
ordered_dict
pattn_issue
pos_bert
pos_charlm
ppf_data
pydataloader
refactor_dataloader
refactor_lstm
refactor_tok
refactor_tokenizer
refactor_tokkenizer_2
runner-demo
semgrex_search_visualization
sentence_ids
sentiment
sentiment_charlm
sentiment_lstm
sentiment_trainer
sindhi
spanish_sent
t5
t5b
tagger_mha
thai-sybrnn
thai_ner
tiny_ud
token
tokens
tr_ner
trans_lm
tweet
ug_ner
update_stanza
updated_eval
updated_eval_2
vi_bert_last
visualization
wandb
word_lstm_pattn
wordinput-sentsegmenter
xpos
Unnamed repository; edit this file 'description' to name the repository.
www-data
summary
refs
log
tree
commit
diff
log msg
author
committer
range
Age
Commit message (
Expand
)
Author
2021-12-14
Add a loss to make the model try to approximate what the classifier would lik...
con_self_gan
John Bauer
2021-12-14
Don't crash if len(pred_batch) == 0
John Bauer
2021-12-14
Stub for treating the classifier as a gan
John Bauer
2021-12-14
Attempt to train the classifier with the parser's best and a random walk nega...
John Bauer
2021-12-14
Rerank the top K based on the results of the classifier. Needs work
John Bauer
2021-12-14
Rename to make this more readable
John Bauer
2021-12-14
Add a useful log line
John Bauer
2021-12-14
7/8ths done? results aren't good yet
John Bauer
2021-12-14
Separate out two parameter groups for different weight_decay values
John Bauer
2021-12-14
Rename for better readability
John Bauer
2021-12-14
Typo
John Bauer
2021-12-14
3/4 finished?
John Bauer
2021-12-14
Half-finished
John Bauer
2021-12-14
Build a classifier layer for in/out (not yet used)
John Bauer
2021-12-14
Initial version of a script to process some IT datasets
John Bauer
2021-12-14
Refactor linear initialization
John Bauer
2021-12-13
Add a line for using a Chinese Roberta from HIT
John Bauer
2021-12-10
Better to catch Exception and not BaseException
John Bauer
2021-12-10
Add some more descriptive error messages and types to prepare_ner_dataset and...
John Bauer
2021-12-10
Move a bunch of tests to more appropriate homes
John Bauer
2021-12-10
If the response encoding isn't set, assume utf-8. Helps on Windows
John Bauer
2021-12-06
Refactor a block of train_one_batch
John Bauer
2021-12-06
tqdm the num_generate
John Bauer
2021-12-05
Separate out the building of output_layers
John Bauer
2021-12-05
Refactor the training step a little bit - no need to pass this information
John Bauer
2021-12-01
Remove empty documents and empty chunks when building selftrain datasets
John Bauer
2021-12-01
Unfinished prototype kbest. Produces extra parses by sometimes taking
John Bauer
2021-12-01
Prototype process single file
John Bauer
2021-11-30
Add rho as a command line parameter for adadelta optimizers
John Bauer
2021-11-28
Update the default weight decay for adadelta and add some comments why
John Bauer
2021-11-26
Refactor the wiki selftrain script so most of the pieces can be reused for vi...
John Bauer
2021-11-25
Don't hide file counter even if we're redirecting to a file
John Bauer
2021-11-25
Use the disable flag instead of making our own crippled tqdm
John Bauer
2021-11-25
num_sentences should be an int
John Bauer
2021-11-25
Add an arg to not shuffle, fix a bug in the file collection
John Bauer
2021-11-25
When building wiki self-training: Recursively traverse the directory, the...
John Bauer
2021-11-24
A tiny bit of doc
John Bauer
2021-11-23
Get the default pretrain for a conparser or ner model from the resources
John Bauer
2021-11-23
Add one doc
John Bauer
2021-11-22
Minor doc improvement
John Bauer
2021-11-22
Merge pull request #885 from stanfordnlp/con_self_attn
John Bauer
2021-11-22
Try a sinusoidal encoding so we don't need a maxlen
John Bauer
2021-11-20
Create N different layers instead of copying the same layer, which may result...
John Bauer
2021-11-20
Allow for the possibility of turning off pattn
John Bauer
2021-11-20
A bit of doc
John Bauer
2021-11-20
Constituency parser: Self-Attention (#877)
hungbui0411
2021-11-20
A rather simple script to retag an existing treebank using the stanza POS and...
John Bauer
2021-11-20
Somewhat unhelpful addition to the oracle
John Bauer
2021-11-20
Attempt AdaBelief and madgrad optimizers (requires a separate install)
John Bauer
2021-11-20
Order the items in a constituency query correctly. Fixes #882
John Bauer
[next]