jfilter / ulmfit-for-germanLinks
π©βπ« Pre-trained German Language Model with sub-word tokenization for ULMFIT
β15Updated 5 years ago
Alternatives and similar repositories for ulmfit-for-german
Users that are interested in ulmfit-for-german are comparing it to the libraries listed below
Sorting:
- The weights for the embedding layer of Scandinavian UMLFiT language modelsβ32Updated 5 years ago
- Sentence transformers models for SpaCyβ107Updated 2 years ago
- Text tokenization and sentence segmentation (segtok v2)β206Updated 3 years ago
- Hunspell extension for spaCy 2.0.β94Updated last year
- Running Prodigy for a team of annotatorsβ53Updated 4 years ago
- Recon NER, Debug and correct annotated Named Entity Recognition (NER) data for inconsistencies and get insights on improving the quality β¦β106Updated last year
- Google USE (Universal Sentence Encoder) for spaCyβ184Updated 2 years ago
- ULMFiT Method for German Languageβ15Updated 6 years ago
- Create interactive textual heat maps for Jupiter notebooksβ196Updated last year
- Character-based word embeddings model based on RNN for handling real worldΒ textsβ174Updated last year
- spaCy + UDPipeβ163Updated 3 years ago
- β69Updated 3 years ago
- PYthon Automated Term Extractionβ316Updated 2 years ago
- Examples for aligning, padding and batching sequence labeling data (NER) for use with pre-trained transformer modelsβ65Updated 2 years ago
- Fuzzy matching and more functionality for spaCy.β258Updated last year
- Information extraction from English and German texts based on predicate logicβ138Updated 2 years ago
- The code to reproduce results from paper "MultiFiT: Efficient Multi-lingual Language Model Fine-tuning" https://arxiv.org/abs/1909.04761β282Updated 5 years ago
- Accelerated NLP pipelines for fast inference on CPU. Built with Transformers and ONNX runtime.β127Updated 4 years ago
- Language Models for Zalando's flair libraryβ61Updated 5 years ago
- LASER multilingual sentence embeddings as a pip packageβ224Updated 2 years ago
- Jupyter Widget for data annotationβ140Updated 2 years ago
- Example using Polyaxon to experiment with pre-training spaCyβ65Updated 3 years ago
- BERTje is a Dutch pre-trained BERT model developed at the University of Groningen. (EMNLP Findings 2020) "Whatβs so special about BERTβs β¦β139Updated 2 years ago
- πΈ fastText + Bloom embeddings for compact, full-coverage vectors with spaCyβ321Updated 5 months ago
- Language detection extension for spaCy 2.0+β113Updated 6 years ago
- spaCy pipeline object for negating concepts in textβ281Updated 3 months ago
- Ensemble topic modelling with pLSAβ114Updated 3 years ago
- xfspell β the Transformer Spell Checkerβ188Updated 5 years ago
- Segment documents into coherent parts using word embeddings.β149Updated 3 years ago
- Topic Inference with Zeroshot modelsβ61Updated 2 years ago