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

Age	Commit message (Expand)	Author
2022-05-01	simplify a bitsentiment_charlm	John Bauer
2022-05-01	Reuse the refactored build_char_representations from the conparse. Seems to ...	John Bauer
2022-05-01	This comment is wrong - it was fixed a long time ago!	John Bauer
2022-05-01	Refactor the extraction of char_representations for lists of words into the c...	John Bauer
2022-05-01	Simplify the usage of charlm a bit in the conparse - no need to keep the char...	John Bauer
2022-04-30	Check that the charlm models given to the conparser go in the right direction	John Bauer
2022-04-30	Merge pull request #1024 from stanfordnlp/sentiment	John Bauer
2022-04-30	Stop passing around device in a bunch of places it isn't really needed	John Bauer
2022-04-30	Simpler, maybe microscopically faster	John Bauer
2022-04-30	Doesn't help figure out why VI is so slow, but interesting to note the model ...	John Bauer
2022-04-30	use initial dev score as best score so far when reloading a model for more tr...	John Bauer
2022-04-30	Switch the VI model to use words tokenized from the stanza tokenizer rather t...sentiment	John Bauer
2022-04-30	Read & write sentiment datasets as json	John Bauer
2022-04-30	Add a path for the vectors	John Bauer
2022-04-30	Unused variable?	John Bauer
2022-04-30	Pass around tokens instead of entire sentences for the sentiment processor	John Bauer
2022-04-29	remove unused import	John Bauer
2022-04-29	Merge pull request #1023 from stanfordnlp/sentiment	John Bauer
2022-04-29	Add an sst2 conversion as well	John Bauer
2022-04-29	Useful logging: how much data is in the train & dev sets	John Bauer
2022-04-29	Refactor a couple non-specific to sentiment confusion matrix operations	John Bauer
2022-04-29	Build a three class root only version of sst	John Bauer
2022-04-29	Update a bunch of comments on how to run - currently we need to produce sst3r...	John Bauer
2022-04-29	Add a binary root only version of the SST conversion	John Bauer
2022-04-29	Pass around lists of tokens instead of single strings. Will make it easier t...	John Bauer
2022-04-29	Convert the .sh prep_sentiment script to .py	John Bauer
2022-04-29	Add an __init__.py to the sentiment scripts directory	John Bauer
2022-04-29	Factor out the loop over TREEBANK_FILES so that we can get phrases for a spec...	John Bauer
2022-04-29	Add debug output to each of the non-sst english sentiment process scripts	John Bauer
2022-04-29	Pass in the root directory to process_arguana_xml.py rather than the inner di...	John Bauer
2022-04-29	Replace the extremely long if/else pattern with a map	John Bauer
2022-04-29	Instead of using -output, capture the output and pass it around as the Fragme...	John Bauer
2022-04-28	Factor out a get_tokenized_phrases for each dataset	John Bauer
2022-04-28	Merge pull request #1022 from stanfordnlp/de_ner	John Bauer
2022-04-28	Add notes on a German model	John Bauer
2022-04-28	Attempt to compensate for German BERT tokenizers not handling soft hyphen ver...de_ner	John Bauer
2022-04-28	Remove the \x96 lines from GermEval2014	John Bauer
2022-04-28	Raise an error if something goes wrong using bert, I guess	John Bauer
2022-04-28	keep_endpoints as an option to bert_embedding instead of something the caller...	John Bauer
2022-04-27	Refactor bert_embeddings so the conparse and ner use the same code. TODO: pe...	John Bauer
2022-04-27	Make all process methods have the same signature	John Bauer
2022-04-27	Add germeval2014 as a conversion	John Bauer
2022-04-27	Better FA option	John Bauer
2022-04-27	minor typo	John Bauer
2022-04-27	Merge pull request #1021 from stanfordnlp/sentiment	John Bauer
2022-04-27	Refactor out the PTB retokenization	John Bauer
2022-04-26	move the scripts/sentiment python scripts to stanza/utils/datasets/sentiment	John Bauer
2022-04-26	Pass around sentiment data using the same namedtuple, making it easier to lat...	John Bauer
2022-04-26	Unify various sentiment scripts to use in/out/shortname	John Bauer
2022-04-26	Refactor main() for all of the sentiment processing scripts	John Bauer