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
2022-08-11
Add a preparation script for Masakhane NER
masakhane
John Bauer
2022-08-11
Make sure a short_name uses the lcode instead of the full language name
John Bauer
2022-08-11
Add two to three letter conversion for better compatibility with Masakhane NER
John Bauer
2022-08-11
canonicalize the casing on treebank names
John Bauer
2022-08-11
Add a method to convert either a short name or an unexpected casing to the ca...
John Bauer
2022-08-11
i forgot what this was supposed to do, so i added some doc once i figured it out
John Bauer
2022-08-11
vertically stripe the short names and full names
John Bauer
2022-08-11
Add some language codes found in Masakhane NER which are not already in our s...
John Bauer
2022-08-10
refactor calculating the checkpoint names - will be reused elsewhere
John Bauer
2022-08-10
A couple notes on other options in the conparser training
John Bauer
2022-08-10
Dropping a reference will hopefully save some GPU memory
John Bauer
2022-08-10
add NER and charlm for Kazakh
John Bauer
2022-08-10
Get vocab from either original charlm format or new charlm + optimizer format...
John Bauer
2022-08-10
One last eval on the last epoch of training. Otherwise the last bit of work ...
John Bauer
2022-08-09
Add a conversion for the publicly available kazNERD dataset for Kazakh
Arman Aydin
2022-08-08
Read <unk> vectors into the UNK_ID row of the embedding
John Bauer
2022-08-08
Add default treebank for lij (Ligurian) to prepare_resources
John Bauer
2022-08-08
Add expected xpos vocabs for the tiny treebanks
John Bauer
2022-08-08
In the event of a UD dataset which has a very small train set and a
John Bauer
2022-08-08
Set up the command line version of convert_it_vit to output debug info for a ...
John Bauer
2022-08-08
config=args for all wandb.init calls
John Bauer
2022-08-08
Improve wandb integration of charlm
John Bauer
2022-08-07
Another VIT link
John Bauer
2022-08-07
Add a link to a paper for VIT. Update the message regarding how to get the V...
John Bauer
2022-08-06
Put global_step and epoch in the Trainer for the charlm. This way, a restart...
John Bauer
2022-08-06
Combine all the children vocabs when listing xpos tags for a CompositeVocab
John Bauer
2022-08-06
whitespace
John Bauer
2022-08-05
Attempt to add th NER model to the resources
John Bauer
2022-08-05
Bugfix in run_depparse: need to use the new wordvec_args method
John Bauer
2022-08-05
handle relative paths to tagger in prepare_depparse_treebank
John Bauer
2022-08-05
Fix some python commands
John Bauer
2022-08-05
Move l3cube to a subdirectory of $NERBASE
John Bauer
2022-08-05
Add a trainer for the charlm - useful for saving and loading everything for c...
John Bauer
2022-08-05
Set random seed with utils (and incidentally fix a namespace->map bug
John Bauer
2022-08-04
Run the charlm for a couple iterations and make sure that doesn't barf
John Bauer
2022-08-04
More descriptive error for empty training data
John Bauer
2022-08-04
Make vars() part of the parse_args call - will simplify use in tests
John Bauer
2022-08-04
Lower learning rate seems to learn better for models of all sizes
John Bauer
2022-08-04
Throw an error if the training or dev data files are empty
John Bauer
2022-08-03
Rough outline of a semgrex interface demo program
John Bauer
2022-08-03
Add the graphIndex and semgrexIndex from CoreNLP 4.5.0 to make the semgrex in...
John Bauer
2022-08-03
Make the error for an unfinished language (hopefully) more useful
John Bauer
2022-08-03
Make a special error type for missing language instead of throwing a ValueError
John Bauer
2022-08-03
Add Saraiki (and fix an alphabetization error)
John Bauer
2022-08-02
Update run_depparse to download word vectors as well
John Bauer
2022-08-02
Automatically download POS (with charlm & wordvec) when redoing depparse
John Bauer
2022-08-02
Oops, need to tell the Trainer where to get the charlm if not in the default ...
John Bauer
2022-08-02
Add a piece of doc
John Bauer
2022-08-02
Download pretrain when training POS
John Bauer
2022-08-02
Add a few more useful output statements to the prepare scripts
John Bauer
[next]