af-ai-center / bert
Code and Swedish pre-trained models for BERT
☆12Updated 4 years ago
Related projects ⓘ
Alternatives and complementary repositories for bert
- The weights for the embedding layer of Scandinavian UMLFiT language models☆33Updated 4 years ago
- ☆138Updated 4 years ago
- Anonymization of legal cases (Fr) based on Flair embeddings☆87Updated 3 years ago
- Pre-trained Nordic models for BERT☆161Updated 3 years ago
- DaNLP is a repository for Natural Language Processing resources for the Danish Language.☆198Updated 11 months ago
- Framework for fine-tuning pretrained transformers for Named-Entity Recognition (NER) tasks☆154Updated last year
- Notebooks configured to be run with Binder, usually found on my blog.☆41Updated last year
- The code to reproduce results from paper "MultiFiT: Efficient Multi-lingual Language Model Fine-tuning" https://arxiv.org/abs/1909.04761☆284Updated 4 years ago
- Language Models for Zalando's flair library☆62Updated 4 years ago
- Dataframe Integration with spaCy.☆101Updated 3 years ago
- NLP French language model implementing ULMFiT☆87Updated 5 years ago
- 📰Natural language processing (NLP) newsletter☆301Updated 4 years ago
- Models and Pipelines for the Spark NLP library☆112Updated 3 years ago
- Running Prodigy for a team of annotators☆53Updated 3 years ago
- Ælæctra was created as part of a Cognitive Science bachelor thesis, in the attempt to enhance the Danish NLP community with a more effici…☆25Updated 2 years ago
- BERTje is a Dutch pre-trained BERT model developed at the University of Groningen. (EMNLP Findings 2020) "What’s so special about BERT’s …☆135Updated last year
- DBMDZ BERT, DistilBERT, ELECTRA, GPT-2 and ConvBERT models☆155Updated last year
- 🤘Lemmy is a lemmatizer for Danish 🇩🇰 and Swedish 🇸🇪☆75Updated 3 years ago
- Natural language processing (NLP) newsletter right on GitHub☆60Updated 4 years ago
- Example using Polyaxon to experiment with pre-training spaCy☆65Updated 3 years ago
- spaCy + UDPipe☆161Updated 2 years ago
- NeuralQA: A Usable Library for Question Answering on Large Datasets with BERT☆231Updated last year
- 💙 Emoji handling and meta data for spaCy with custom extension attributes☆180Updated last year
- 📂 Additional lookup tables and data resources for spaCy☆98Updated last year
- Toolkit to help understand "what lies" in word embeddings. Also benchmarking!☆469Updated last year
- BERT model trained from scratch on Finnish☆96Updated 3 years ago
- Deep learning with text doesn't have to be scary.☆275Updated last year
- Fuzzy matching and more functionality for spaCy.☆252Updated 4 months ago
- A Dutch RoBERTa-based language model☆197Updated 7 months ago
- A system for generating training labels via natural language explanations☆146Updated 5 years ago