stanza
stanza copied to clipboard
Stanford NLP Python library for tokenization, sentence segmentation, NER, and parsing of many human languages
Corenlp can visualize annotations using brat.js At the same time, an object in json format valid for brat operation is delivered from the server.js How can I convert to the...
For several languages (e.g. German) there are several UD models and also several NER models. Also there is an evaluation of the different NER models. However, I cannot find any...
This line: https://github.com/stanfordnlp/stanza/blob/main/stanza/pipeline/core.py#L169 Please export `stanza.DownloadMethod` so one could write: ```` stanza.Pipeline( ..., download_method=stanza.DownloadMethod.NONE, ... ) ````
**Motivational problem** We can use `CoreNLPClient` just as client interface to interact with an already existent CoreNLP standalone server by passing the argument: `start_server=StartServer.DONT_START` But in this cases if the...
  i have installed java, and also get this error
For example to provide a list of abbreviations and tell the model to avoid splitting the token if it belongs to the list. This would be very useful to improve...
Hi everyone! I noticed that since v1.2.0 (https://github.com/stanfordnlp/stanza/releases) English and Italian models combine different treebanks "and a custom dataset including MWT tokens". Now, italian pronouns - both MWT and single...
Hello , Could any let know what is the correct format of data to train sentiment mode and the way to train it? how to train it for few scentences...
The Kurmanji (Kurdish) model, although listed in "Available Models & Languages", cannot be downloaded. When trying stanza.download('kmr') you get the error: An error ValueError: Unsupported language: kmr. I guess the...