stanza · Issues· 95 open

bhojpuri (bho): POS model support

FoundationCache holds global lock across heavy model loads, serializing concurrent pipeline initialization

Craft, Genia, Mimic bio models not using MWT

RU charlm is not helping much

Typo=Yes in the feats column of MWT does not survive a round trip

The English MIMIC lemmatizer fails to initialize with a KeyError

MWT token ids become lists after to_serialized, producing invalid CoNLL-U

Is there a way to feed speaker information to the coref processor?

constituency parser could use the learning rate scheduler from depparse

Please publish your security advisories

English tokenizer regression in 1.13.0: sentence boundaries inserted mid-sentence around numerals in proper-noun phrases

Dependency parsing: is there some way to discourage multiple `nsubj` dependents?

DE training data extension to fix grammar parsing bugs

Switch from oscar 2023 to oscar community

generating conllu instead of text from sloleks