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
2022-07-16
Merge branch 'dev' into thai_ner
thai_ner
John Bauer
2022-07-16
VI backup files
John Bauer
2022-07-16
Remove vi .swp file
John Bauer
2022-07-16
Merge branch 'dev' into thai_ner
John Bauer
2022-07-16
Document visualization with Spacy. Processes completed docs or raw strings
SecroLoL
2022-07-16
Move print statement
John Bauer
2022-07-16
rm
John Bauer
2022-07-16
Tiny changes
John Bauer
2022-07-16
Undo path changes
John Bauer
2022-07-16
Merge branch 'dev' into thai_ner
John Bauer
2022-07-16
Update the xpos chart for UD 2.10
John Bauer
2022-07-16
Add alternatives for alternate names for treebanks and add en_test
John Bauer
2022-07-16
Update build_xpos_vocab_factory to use argparse and get the list of treebanks...
John Bauer
2022-07-16
fix bert_embedding max length
Kantapong Kotchum
2022-07-16
Oops, should just return the short_name when this happens
John Bauer
2022-07-15
Upgrade the initial punct augmentation to handle additional deps and copy nodes
John Bauer
2022-07-15
Use SHORT_NAMES to allow for the prepare scripts to use the short name to spe...
John Bauer
2022-07-15
Add an alternate name for no_bokmaal to short_name_to_treebank
John Bauer
2022-07-15
Update short_name_to_treebank.py for UD 2.10
John Bauer
2022-07-15
This comment is out of date
John Bauer
2022-07-15
Update the error for a misformated dictionary-in-parts with more information ...
John Bauer
2022-07-15
Give a more useful error when this comes up, rather than the difficult to int...
John Bauer
2022-07-14
Mask illegal langauges by setting them to -ninf. 0 means that illegal langua...
John Bauer
2022-07-14
Barf if the subprofess commands in make_lm_data fail
John Bauer
2022-07-14
Add an error if not enough files are produced to make train/dev/test
John Bauer
2022-07-14
Ignore wandb and stanza_resources
John Bauer
2022-07-13
Add an error if there isn't enough data for a charlm
John Bauer
2022-07-13
Move default location to under a thai subdirectory
John Bauer
2022-07-13
Merge branch 'dev' into thai_ner
John Bauer
2022-07-13
fix LOC_I
Kantapong Kotchum
2022-07-13
fix LOC-I tag
Kantapong Kotchum
2022-07-12
fix error in prepare_ner_dataset for thai language
Kantapong Kotchum
2022-07-12
Make bidirectional an option in the POS model. If it helps, though, it's a v...
John Bauer
2022-07-12
Whitespace update
John Bauer
2022-07-11
Move the random seed into the conversion method, in case people convert multi...
John Bauer
2022-07-11
Update convert_fire_2013.py
anwesham-lab
2022-07-11
One attempt at reducing the tag space for hi_ner. Not super great
John Bauer
2022-07-10
Read in a pretrain even if it doesn't have a row/col header. This applies to...
John Bauer
2022-07-09
Merge branch 'dev' into thai_ner
John Bauer
2022-07-09
Log the tags present in the training set when starting an NER training run
John Bauer
2022-07-09
Split on tabs instead of spaces - many of the LST20 tokens have spaces in them
John Bauer
2022-07-09
Merge branch 'dev' into thai_ner
John Bauer
2022-07-09
Allow underscores as well as dashes
John Bauer
2022-07-09
Merge branch 'dev' into thai_ner
John Bauer
2022-07-09
Don't try to download pretrains for models where we don't have one by default
John Bauer
2022-07-09
Be a little more clear about not using all the vectors
John Bauer
2022-07-08
We always set this to 100000 when training new models, so might as well make ...
John Bauer
2022-07-08
Merge branch 'dev' into thai_ner
John Bauer
2022-07-08
include code to process conllu dataset into json format
Kantapong Kotchum
2022-07-07
Add getting all possible values for each feat
Karol Saputa
[next]