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.
summaryrefslogtreecommitdiff
AgeCommit message (Expand)Author
2022-10-29refactor predict dir,file,format args so they can be used elsewhere if neededJohn Bauer
2022-10-29Refactor an unnecessary duplication of argumentsJohn Bauer
2022-10-29Add functionality to turn a tokenized text file into a file of parse treesJohn Bauer
2022-10-29ignore em dashes in Wikipedia, as that seems to be listsJohn Bauer
2022-10-29Add a useful doc on how to build batches from tagged wordsJohn Bauer
2022-10-29Use reasonable defaults for EN and VI ensembles. Can add other languages as ...John Bauer
2022-10-29Oops, logger was missing in the retagging.py moduleJohn Bauer
2022-10-29A script for tokenizing a Wikipedia file and writing it outJohn Bauer
2022-10-28Accept a single file for wiki processing in selftrain_wiki.pyJohn Bauer
2022-10-28fix bug in the lt/gt finding (it can start a line). use FoundationCache to s...John Bauer
2022-10-28Add a rotation to make N non-overlapping dev sets with the remainder being tr...John Bauer
2022-10-28Simplify reading & writing loop. Will make it easier to 'rotate' the dev setJohn Bauer
2022-10-28Add a prototype of model emsembling. Better would be to integrate it with ru...John Bauer
2022-10-28Refactor the retagging args & pipeline creation into a separate modeuleJohn Bauer
2022-10-28Keep scores when parsing a block of sentences.John Bauer
2022-10-28fix a commentJohn Bauer
2022-10-27Order the pretrains so that resource files are made with a consistent md5sumJohn Bauer
2022-10-27Add an extraction for bartphoJohn Bauer
2022-10-27Sort files when converting VLSP22 so that output is the same across platformsJohn Bauer
2022-10-27Adjust attention masks for vi phobertJohn Bauer
2022-10-27add a line for using phobert on the vlsp tagger datasetJohn Bauer
2022-10-26Existing POS models with bert would be broken when looking at the args, so in...John Bauer
2022-10-26Fix retag package when using relabel_tagsJohn Bauer
2022-10-26mix N layers of transformer when adding them to the POS inputsJohn Bauer
2022-10-26Mark this test with travis - not sure that is still relevantJohn Bauer
2022-10-25Add a --predict_format option which will allow the user to specify how to wri...John Bauer
2022-10-25By default, use _ to separate spaces when converting pase trees to LMJohn Bauer
2022-10-24Return 2 values if the dev/test set is emptyJohn Bauer
2022-10-24Sort VLSP filenames to avoid cross-platform weirdnessJohn Bauer
2022-10-24batch -> training_batch or current_batch as relevantJohn Bauer
2022-10-24Add a hopefully useful docJohn Bauer
2022-10-23Add a trivial parse_tagged_words testJohn Bauer
2022-10-23By default, turn off pattn & lattn (at least until we figure out how to extra...John Bauer
2022-10-23Notes on default bert model. More hidden layers for VI bert by defaultJohn Bauer
2022-10-22Add a tool which connects to the ProcessMorphologyRequest in CoreNLP (not rel...John Bauer
2022-10-22Update corenlp.proto with definitions that will connect to the Morphology ann...John Bauer
2022-10-22Process a constituency treebank into a POS dataset. Note that spacing, lemma...John Bauer
2022-10-22Print trees in the output format VLSP expects for the bakeoffJohn Bauer
2022-10-22Fully specify format to avoid warning, test the basic output as wellJohn Bauer
2022-10-22Option to convert LBKT to -LRB-, RBKT to -RRB-John Bauer
2022-10-21Clean up use of full_results vs treebankJohn Bauer
2022-10-21fix --num_generate bugJohn Bauer
2022-10-21Apparently this one detach().cpu() call speeds up the program by 5%John Bauer
2022-10-21Add an option to the vlsp22 processing to load from a different pathJohn Bauer
2022-10-21Reorganize prepare_con_dataset to use the same function header for all functi...John Bauer
2022-10-21Count a couple other stray tags as errors - they are all now fixed in the 202...John Bauer
2022-10-20A couple upgrades to the IT silver script and the silver scripts in general -...John Bauer
2022-10-20Disallow a bunch more constituents - although now the 2022 dataset is mostly ...John Bauer
2022-10-20Fix a couple trees which were weirdly labeledJohn Bauer
2022-10-20Don't process .zip files when doing vlsp-22John Bauer