release/444-release-candidate

[maziyarpanahi]

4.4.4

New Features & Enhancements

• Add Warmup stage to loading all Transformers for word embeddings: ALBERT, BERT, CamemBERT, DistilBERT, RoBERTa, XLM-RoBERTa, and XLNet. This helps reducing the first inference time and also validate importing external models from HuggingFace SPARKNLP 801 set up warmup for all embeddings #13851
• Add new notebooks to import ZeroShot Classifiers for Bert, DistilBERT, and RoBERTa fine-tuned based on NLI datasets SPARKNLP-815: Add examples for ZeroShotClassifiers #13845

---

Bug Fixes

• Fix not being able to save models from XXXForSequenceClassitication and XXXForZeroShotClassification annotators Resolve saving bug with multilabel parameter #13842
• Fix pretrained pipelines that stopped working since the 4.4.2 release on PySpark 3.2 and 3.3 versions (adding 121 new pipelines were added) 2023-05-27-explain_document_md_fr #13836