Ermlab / PoLitBert
Polish RoBERTA model trained on Polish literature, Wikipedia, and Oscar. The major assumption is that quality text will give a good model.
☆33Updated 3 years ago
Related projects ⓘ
Alternatives and complementary repositories for PoLitBert
- RoBERTa models for Polish☆86Updated 2 years ago
- A monolingual and cross-lingual meta-embedding generation and evaluation framework☆80Updated 2 years ago
- Evaluation of Sentence Representations in Polish☆22Updated last year
- Augmenty is an augmentation library based on spaCy for augmenting texts.☆151Updated 5 months ago
- This repository contains an easy and intuitive approach to few-shot NER using most similar expansion over spaCy embeddings. Now with enti…☆242Updated last year
- ☆50Updated 2 years ago
- Code and data accompanying the paper "Approaching nested named entity recognition with parallel LSTM-CRFs."☆26Updated last year
- Recon NER, Debug and correct annotated Named Entity Recognition (NER) data for inconsistencies and get insights on improving the quality …☆106Updated 8 months ago
- A library to synthesize text datasets using Large Language Models (LLM)☆151Updated last year
- A Python library aimed at dissecting and augmenting NER training data.☆56Updated last year
- Polish BERT☆70Updated 4 years ago
- A multi-lingual approach to AllenNLP CoReference Resolution along with a wrapper for spaCy.☆103Updated 6 months ago
- Fine-tuning scripts for evaluating transformer-based models on KLEJ benchmark.☆24Updated last year
- Custom Natural Language Processing with big and small models 🌲🌱☆68Updated 3 years ago
- Shared BERT model for 4 languages of Bulgarian, Czech, Polish and Russian. Slavic NER model.☆73Updated 2 years ago
- A spaCy custom component that extracts and normalizes temporal expressions☆52Updated last year
- All the goto functions you need to handle NLP use-cases, integrated in NLPretext☆139Updated 7 months ago
- classy is a simple-to-use library for building high-performance Machine Learning models in NLP.☆85Updated last month
- Pipeline component for spaCy (and other spaCy-wrapped parsers such as spacy-stanza and spacy-udpipe) that adds CoNLL-U properties to a Do…☆76Updated 4 months ago
- 🧪 Cutting-edge experimental spaCy components and features☆95Updated 6 months ago
- Information extraction from English and German texts based on predicate logic☆135Updated last year
- A High-level Library for Named Entity Recognition in Python.☆23Updated 11 months ago
- Explainable Zero-Shot Topic Extraction☆61Updated 2 months ago
- Creating class-based TF-IDF matrices☆82Updated 2 years ago
- Full named-entity (i.e., not tag/token) evaluation metrics based on SemEval’13☆157Updated this week
- 🌸 fastText + Bloom embeddings for compact, full-coverage vectors with spaCy☆286Updated last year
- ☆147Updated 4 months ago
- Some notebooks for NLP☆187Updated last year
- ☆60Updated 3 years ago
- A spaCy wrapper of Entity-Fishing (component) for named entity disambiguation and linking on Wikidata☆152Updated 2 years ago