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
2021-08-10
Also check if the test set has tags not present in the tagger or if the train...
v1.2.3
John Bauer
2021-08-10
Add a test to see if any tags are in the dev set but not the train set
John Bauer
2021-08-10
Change file not found to an error
John Bauer
2021-08-10
Add two new NER models to the resources
John Bauer
2021-08-10
This test was backwards, causing a bunch of stray java processes when a conte...
John Bauer
2021-08-10
Update word embedding to the dimension in the file when creating a new model
John Bauer
2021-08-10
Double check that the length of the processors list is 2 when adding just tok...
John Bauer
2021-08-10
Add mwt if tokenize is passed without MWT (#777)
David Riff
2021-08-10
Add some explanation to the logging output for the NER scores
John Bauer
2021-08-10
Add processing for it_fbk. Uses the .tsv file they sent us and their recomme...
John Bauer
2021-08-10
Add the ability for the ner model to upscale basic (no B- or I-) tagging -> B...
John Bauer
2021-08-10
Add a processing step for NHCLT datasets. Currently Afrikaans is the most us...
John Bauer
2021-08-10
Make the matrix more readable when there are a ton of categories
John Bauer
2021-08-10
Format ints differently from floats in the confusion matrix
John Bauer
2021-08-10
Add a confusion matrix over tokens to the output of the ner_tagger
John Bauer
2021-08-10
Separate the test of the scorer from the test of the ner_tagger itself
John Bauer
2021-08-10
Add some more command lines to the prepare_ner_dataset.py doc
John Bauer
2021-08-10
Make a version 1.2.3 with a couple minor bugfixes
John Bauer
2021-08-10
Add a test of empty text for the pipeline
John Bauer
2021-08-10
Test updates based on changes to the underlying data, which changed the resul...
John Bauer
2021-08-10
Test updates based on changes to the underlying data, which changed the resul...
John Bauer
2021-08-10
Add a flag for finetuning from a different load name from the save_name
John Bauer
2021-08-10
If given an empty list, simply return an empty list when sort is called. Fix...
John Bauer
2021-07-13
Merge pull request #749 from stanfordnlp/1.2.2
v1.2.2
John Bauer
2021-07-11
Update version and resources to 1.2.2
John Bauer
2021-07-11
Add a VI NER model
John Bauer
2021-07-10
Minor whitespace change
John Bauer
2021-07-10
Give a reason for failing if the md5sum doesn't match
John Bauer
2021-07-10
Fix pickling issue on Windows with lambdas
Bram Vanroy
2021-07-10
Fix a typo
John Bauer
2021-07-10
Make an error message more useful
John Bauer
2021-07-10
Add some comments on the common.py main method
John Bauer
2021-07-10
Add & clarify some comments on run_ner.py
John Bauer
2021-07-10
Switch a bunch of % to f-strings
John Bauer
2021-07-10
Get the char_hidden_dim from the charlm if a charlm is used
John Bauer
2021-07-10
Pass the charlm filenames to the trainer so that different charlm locations c...
John Bauer
2021-07-10
Convert the run_ner.sh script to python
John Bauer
2021-07-10
Make prepare_ner_dataset runnable as a module
John Bauer
2021-07-10
Add explicit flags for specifying where the charlm files are. Will still gue...
John Bauer
2021-07-10
Sort and then unsort the text by length in the sentiment processor. Use this...
John Bauer
2021-07-10
Only normalize spaces -> nbsp in the pretrain vocabs
John Bauer
2021-07-10
Gotta save two seconds when running the tests
John Bauer
2021-07-10
Add a specialized bulk_process for NER, along with a small unit test
John Bauer
2021-07-02
Fix bibtex
Yuhao Zhang
2021-07-02
Update bibtex
Yuhao Zhang
2021-06-09
Merge pull request #719 from stanfordnlp/dev
v1.2.1
John Bauer
2021-06-08
Merge pull request #718 from stanfordnlp/ud28
John Bauer
2021-06-07
Alert if the json file can't be downloaded, which can happen if someone forge...
John Bauer
2021-06-04
Save memory when building a charlm out of a single file
John Bauer
2021-06-03
Add the currently unused languages to the constants files. Regenerate short_...
John Bauer
[next]