stanza

stanza copied to clipboard

Low performance in many-cores systems

1

**Describe the bug** When Stanza run from docker container at the server with more then ~20 cores - performance of the pipeline falling dramatically. **To Reproduce** 1) Get machine with...

StarTessar

Check for and replace excessively long tokens with "UNK"; addresses issue 1137

10

## Description Added a check to find & replace excessively-long tokens with "UNK", in order to avoid downstream GPU memory in `POS`. See issue #1137 ## Approach To avoid having...

khughitt

Add a script to convert from AWS annotator reports to a report on how much work each annotator did

AngledLuffa

Transliterate kazakh to a latin alphabet

AngledLuffa

Handle unexpectedly large tokens prior to calling the pos, etc. processors?

6

**Problem / motivation** When processing large corpuses of text, the likelihood of encounter unexpected and ill-formatted inputs becomes large. In my case, I was processing a collection of texts, and...

khughitt

Mismatched token output using custom stanza tokenizer

3

**Describe the bug** I trained a custom stanza tokenizer and mwt on UD_English-GUM. When using the tokenizer & mwt for inference, the tokenizer changed the surface form of the word....

yilunzhu

How to replicate results of stanza constituency parser on Penn Treebank data

4

Hi, I'm trying to reproduce the results mentioned [here](https://stanfordnlp.github.io/stanza/constituency.html#available-models) for constituency parser on Penn treebank data. I have access to wsj data and I downloaded the `wsj_bert.pt` model by calling...

MHDBST

More combined models?

59

I saw the great idea for combined models here: https://stanfordnlp.github.io/stanza/combined_models.html Is there a process to request more of these? Specifically I was thinking of Hebrew right now.

amir-zeldes

Inaccurate Dependency Tagging for Subordinates (ccomp)

18

Greetings all, I working on extracting subordinate clauses via Stanza (Indeed through spacy-stanze); however, dependency parsing seems to provide inaccurate results. Following the guide from https://universaldependencies.org [here](https://universaldependencies.org/u/dep/csubj.html), clausal subjects are...

fatihbozdag

[QUESTION] Rebuilding an existing language from sources

9

This is my first question, so sorry if I make any mistake, but I haven't had found information about rebuilding an exsiting language from its sources. I plan doing this...

student-nlp-project