stanza

stanza copied to clipboard

Arabic model: wrong sentence splitting (PADT)

3

I am trying to parse Arabic texts using the pretrained model (PADT), but some portions of texts are recognized as a single sentence. For example, this Arabic passage results in...

rahonalab

FutureWarning: You are using `torch.load` with `weights_only=False`

1

**Describe the bug** FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which...

mskaif

NER error after loading a CONLL-U document: doc.text is None

1

I get the following error when running NER: `TypeError: 'NoneType' object is not subscriptable` After debugging the error, I found out that it is trying to access the document's `text`...

zbeloki

Poor NER performance?

1

I am using Stanza to identify NER is short pieces of text like (business names/brand names). Here is one example: ``` # BUILDING THE MODELS #-----stanza sen = stanza.Pipeline ("en")...

stajdini

Add a word classifier to cover ambiguous lemmas such as `'s`

AngledLuffa

create a second tokenization stage which uses contextual *word* embeddings as well token embeddings to be more accurate. Doesn't seem to help for languages with clearly delinated orthographies but in...

Jemoka

Portuguese model mistakenly splits URLs into their own sentences

3

**Describe the bug** When a Pipeline is instantiated with a text containing some URLs (e.g. example.com) in Portuguese, the URLs are broken into their own sentences, as the dots are...

busdriverbuddha

**Description:** I have encountered an issue with the Stanza pipeline for the Indonesian language, specifically with the tokenizer processor. The pipeline fails to handle sentence segmentation properly when a sentence...

nxgeo

it should not be necessary for download to call set_logging_level we could have a separate logging specifically for the downloads if we want to log the downloads at a higher...

AngledLuffa

French regression between Stanza 1.8.1 and 1.8.2

16

**Describe the bug** Take the following sentence: **Assurez-vous d'être à l'heure !** The word vous has a wrong dependency relation with Stanza 1.8.2, but correct with Stanza 1.8.1 Stanza 1.8.1...

blegaut