stanza

stanza copied to clipboard

> Sorry for dropping this on the floor. Actually, it's pretty straightforward, so there's not really a good excuse for making you wait. > > > > ``` > >...

IsaacFigNewton

How to implement negation to entities and link disease to UMLS?

5

Hi folks, I am just new to Sandfordnlp and found it better compared to other methods. I would like to know how to implement negations to entities as like negspacy...

Raghu17s

[QUESTION]Missing documentation

1

This page https://stanfordnlp.github.io/stanza/pipeline.html in the description of the package option says "A complete list of available packages can be found [here](https://stanfordnlp.github.io/stanza/models.html)." However there is no list of packages at the...

Denis-Kazakov

Coref model skipping long documents during training

3

I have been investigating the code for the coreference model to better understand its inner workings. One thing that caught my attention is that during training documents longer than 5,000...

501Good

I would like a way to deploy stanza models in web environments, i.e. using pyodide. I imagine that dependencies are the biggest (insurmountable?) hurdle blocking this feature. It does not...

reynoldsnlp

Batch processing differs in tagging output from single document processing

8

Hello! We have been using Stanza 1.10.1 with single document processing but want to switch to batch processing to increase speed. For that, we ran some benchmarks, among other things...

DZNLP

Wrong genders in Romanian

5

**Describe the bug** When tokenizing neuter words in Romanian, they are tagged as "Gender=Masc" **To Reproduce** Analyze a sentence such as "Sistemul este foarte bun". The neuter noun "sistem" appears...

jonnyGitHub57

Add NER for Urdu pipeline

3

**Is your feature request related to a problem? Please describe.** Stanza promises some basic functionalities for all languages but NER is not implemented for Urdu yet. **Describe the solution you'd...

thani-ath-nain-khurshid

Discontinuous mentions in the coref model

4

Hello! **Is your feature request related to a problem? Please describe.** Currently, a closing index of a discontinuous mention is not captured by the regex in the [convert_udcoref.py](https://github.com/stanfordnlp/stanza/blob/af3d42b70ef2d82d96f410214f98dd17dd983f51/stanza/utils/datasets/coref/convert_udcoref.py) script. For...

501Good

bulk_process of CoNLL-U Documents throws error in process_pre_tokenized_text()

4

When I import a single CoNLL-U Document via CoNLL.conll2doc and then run a pipeline with tokenize_pretokenized=True, tokenize_no_ssplit=True on it, it gets processed without problems. However, when I put several CoNLL-U...

rohlik-hu