github.com/stanfordnlp/stanza.git - Unnamed repository; edit this file 'description' to name the repository.

Age	Commit message (Expand)	Author
2022-08-05	Add a trainer for the charlm - useful for saving and loading everything for c...charlm_checkpoint	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
2022-08-02	Add a hopefully useful status line to the preparation script	John Bauer
2022-08-02	2.10 is the most recent version	John Bauer
2022-08-02	Explicitely remove unsaved modules from the optimizer, although this doesn't ...	John Bauer
2022-08-01	Add an option for an alternate output directory if needed	John Bauer
2022-08-01	Convert oscar 2022 files to txt by extracting the content fields	John Bauer
2022-08-01	Making combining the input the default for the lattn layer	John Bauer
2022-07-30	Rename Fragment -> SentimentDatum to make a more understandable name for pote...	John Bauer
2022-07-30	Further refactor - put the utility method in the utility methods file	John Bauer
2022-07-30	Refactor - the MR sentiment dataset can use the 'write_dataset' function	John Bauer
2022-07-30	Also remove ufeff	John Bauer
2022-07-30	Strip words ... only changes one word in bn_daffodil	John Bauer
2022-07-29	Refactor read_datasets from the bn_daffodil NER script. May be useful for bu...	John Bauer
2022-07-29	bert & roberta attention masks	John Bauer
2022-07-29	Restore a sentence to VIT that seems to be fixed in the latest updates	John Bauer
2022-07-29	Update to use the latest version of Italian VIT constituency treebank from ELRA	John Bauer
2022-07-29	Some minor updates to the VIT constituency processing based on more text upda...	John Bauer
2022-07-29	Update comments and paths for building constituency it_vit to reflect the lat...	John Bauer
2022-07-29	Add a bunch of languages represented in fasttext vectors	John Bauer
2022-07-29	exceptions and logging with periods separated from the language names for rea...	John Bauer
2022-07-27	Latest POS models change this word to NOUN	John Bauer
2022-07-26	Integrate xlnet	John Bauer
2022-07-26	Use the next token instead of the last token for the endpoint in bert - makes...	John Bauer
2022-07-25	Oops, bugfix - the start & end tokens take up space in the bert tokenizer	John Bauer
2022-07-24	Updated tagger tags Opal as a noun (perhaps we should choose a more stable te...	John Bauer
2022-07-22	Save NER models if the training hasn't gone on long enough to hit a checkpoint	John Bauer
2022-07-21	Load the pretrained charlm, adds it as inputs to the POS model	John Bauer
2022-07-20	Small whitespace change	John Bauer
2022-07-20	Upgrade convert_pretrain to read from .csv files	John Bauer
2022-07-20	Add a reader for .csv files to the pretrained embedding reading function	John Bauer
2022-07-20	Move logging inside read_from_file	John Bauer
2022-07-20	Failed lines are now dropped inside read_from_file	John Bauer
2022-07-20	Test that the en_ewt with an unexpected tagset logs an error. All other test...	John Bauer
2022-07-20	Put the xpos vocab test in a class so we can level it up	John Bauer