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
2022-04-23
Update version to 1.4.0 instead of 1.3.1 - enough fancy changes such as addin...
v1.4.0
John Bauer
2022-04-23
Add the ability to use an alternate_md5 to accept a file. Will allow resourc...
John Bauer
2022-04-23
Use ValueError and FileNotFoundError instead of assert for unexpected md5
John Bauer
2022-04-23
depparse requires lemmatization to get the right results
John Bauer
2022-04-23
New models get the features correct
John Bauer
2022-04-23
Don't 'augment' the MWT dataset for Italian
John Bauer
2022-04-23
Use the handparsed treebank as part of the en_combined models
John Bauer
2022-04-23
Allow for download_method==None, to make things simpler
John Bauer
2022-04-23
Add a JA charlm
John Bauer
2022-04-23
fix: move pe to the appropriate device
zhaochaocs
2022-04-23
Throw an error if any trees are discarded - the most up-to-date VIT should not
John Bauer
2022-04-23
Finish converting tokens in VIT not matched by more general rules
John Bauer
2022-04-23
Reading errors are now uncommon enough that we can just output them all
John Bauer
2022-04-23
Another common abbreviation in the VIT dataset
John Bauer
2022-04-23
Put the NER and MULTI_NER at the end of the token dict. This will make the c...
John Bauer
2022-04-23
Update a broken doc
John Bauer
2022-04-23
Write NER tags to conll docs
John Bauer
2022-04-23
Eliminate redundant declarations of various constants
John Bauer
2022-04-23
Add some doc for the use of tempfile
John Bauer
2022-04-23
Download files to a tempdir created underneath the expected destination, then...
John Bauer
2022-04-23
Process sentence ids from the corpus, if available.
John Bauer
2022-04-23
Add a second block of text to a data conversion text - make sure that multipl...
John Bauer
2022-04-23
all conparser checkpoints now have unary_limit and args baked in
John Bauer
2022-04-23
Add a tool for removing unwanted optimizers from conparser models
John Bauer
2022-04-23
Save a couple useful items in the constituency model save files - unary_limit...
John Bauer
2022-04-23
A couple minor changes that came up when removing optimizers from conparser m...
John Bauer
2022-04-23
Move the SHORTNAME_RE from the dataset/training tools to treebank_to_short_na...
John Bauer
2022-04-23
Add a comment regarding why there's a separate method here
John Bauer
2022-04-23
All existing models for the next version now have params baked in as expected
John Bauer
2022-04-23
Factor out the args when building a trainer. Useful for building multiple mo...
John Bauer
2022-04-23
Combine stats in a single tuple to make it cleaner to pass around
John Bauer
2022-04-23
Add an error specifically for extra ) when reading a tree file
John Bauer
2022-04-23
Rename and clarify a comment
John Bauer
2022-04-23
model is never None
John Bauer
2022-04-23
remove confusing capitalization
John Bauer
2022-04-23
use the updated version of VIT from prof. delmonte
John Bauer
2022-04-23
Rename a bunch of parameters to make similar things have similar names. Rear...
John Bauer
2022-04-23
Update default con datasets & add a couple more
John Bauer
2022-04-23
Allow for conparser with no charlm
John Bauer
2022-04-23
Optimizer step after calling a batch. Useful for doing batches from differen...
John Bauer
2022-04-23
Add a citation for the FBK NER dataset
John Bauer
2022-04-23
Attempt to make sure all tensors are created on the correct device in the par...
John Bauer
2022-04-23
Oops, busted for copy/paste of the unit test's skeleton
John Bauer
2022-04-23
Converting VIT for constituencies
John Bauer
2022-04-23
Refactor the write_dataset function
John Bauer
2022-04-23
Extract the sentence.text from the comments, such as when reading in UD docum...
John Bauer
2022-04-23
Remove unnecessary option to not provide a reusable tsurgeon processor
John Bauer
2022-04-23
Unroll the recursion
John Bauer
2022-04-23
Refactor - refactor some common blocks of code for processing the scores matr...
John Bauer
2022-04-23
Refactor - turn the solved results of a chu liu edmonds subproblem into a sol...
John Bauer
[next]