allegro / HerBERTView external linksLinks
HerBERT is a BERT-based Language Model trained on Polish Corpora using only MLM objective with dynamic masking of whole words.
☆70Feb 3, 2022Updated 4 years ago
Alternatives and similar repositories for HerBERT
Users that are interested in HerBERT are comparing it to the libraries listed below
Sorting:
- Fine-tuning scripts for evaluating transformer-based models on KLEJ benchmark.☆26Jul 6, 2023Updated 2 years ago
- Generic framework for information extraction tasks, including recognition of named entities, temporal expressions, spatial expressions an…☆13Jun 5, 2023Updated 2 years ago
- A curated list of resources dedicated to Natural Language Processing (NLP) in polish. Models, tools, datasets.☆307Aug 8, 2021Updated 4 years ago
- RoBERTa models for Polish☆90Mar 8, 2022Updated 3 years ago
- Polish morphological tagger.☆43May 22, 2023Updated 2 years ago
- Polish RoBERTA model trained on Polish literature, Wikipedia, and Oscar. The major assumption is that quality text will give a good mode…☆35May 25, 2021Updated 4 years ago
- COMBO is jointly trained tagger, lemmatizer and dependency parser.☆36Mar 24, 2023Updated 2 years ago
- Python port of Stempel, an algorithmic stemmer for Polish language.☆39Aug 29, 2024Updated last year
- Polish BERT☆72Oct 27, 2020Updated 5 years ago
- ☆51Aug 22, 2022Updated 3 years ago
- Code and data accompanying the paper "Approaching nested named entity recognition with parallel LSTM-CRFs."☆27Dec 8, 2022Updated 3 years ago
- Tool for named entity recognition for Polish based on deep learning.☆31Mar 24, 2023Updated 2 years ago
- Evaluation of Sentence Representations in Polish☆23Dec 29, 2022Updated 3 years ago
- Embeddings: State-of-the-art Text Representations for Natural Language Processing tasks, an initial version of library focus on the Polis…☆37Dec 3, 2023Updated 2 years ago
- Pre-trained models and language resources for Natural Language Processing in Polish☆370Jun 5, 2024Updated last year
- A baseline Automatic Speech Recognition system for Polish based on Kaldi.☆18Dec 21, 2021Updated 4 years ago
- A Python framework for data processing on GCP.☆120Apr 9, 2025Updated 10 months ago
- Utilities for manipulating finite state transducers with the OpenFst library.☆32Sep 22, 2017Updated 8 years ago
- A Tree-LSTM-based dependency tree sentiment labeler☆15May 9, 2019Updated 6 years ago
- Crash Course in Reinforcement Learning - ML in PL workshops☆20Feb 20, 2020Updated 5 years ago
- Polish data.☆12Nov 12, 2025Updated 3 months ago
- Resources for doing NLP in Polish☆48Nov 4, 2019Updated 6 years ago
- Inforex is a web system for text corpora construction.☆12Jun 26, 2025Updated 7 months ago
- A curated list of events, hackathons, and communities focused on AI and tech in Poland☆29Aug 21, 2025Updated 5 months ago
- Multilingual text corpus designed to study multilingual and cross-lingual natural language understanding (NLU) models and the strategies …☆13Jun 15, 2025Updated 8 months ago
- ☆30Nov 22, 2022Updated 3 years ago
- Fast CRUD implemetation for Django.☆14Mar 22, 2025Updated 10 months ago
- Scripts for preprocessing morfologik data.☆40Dec 2, 2017Updated 8 years ago
- Frontless Swift - replaces Javascript with Swift for convenient and reactive web experiences.☆16Jan 1, 2022Updated 4 years ago
- ☆16Dec 30, 2018Updated 7 years ago
- Instruct-tune LLaMA on consumer hardware☆21Apr 2, 2023Updated 2 years ago
- A very simple python stemmer for Polish language based on Porter's Algorithm☆20Dec 4, 2017Updated 8 years ago
- The Python interface to the Hermes message broker.☆19May 27, 2025Updated 8 months ago
- SwiftBox is a package that helps building Swift/Vapor microservices.☆21Apr 17, 2023Updated 2 years ago
- ☆20Nov 25, 2018Updated 7 years ago
- Natural language processing course thought at AGH University of Science and Technology☆68Dec 1, 2025Updated 2 months ago
- Creates the inverse of transliterated string to a regex. What? Basically, diacritic insensitiveness☆28Nov 15, 2025Updated 3 months ago
- Repository for our ACL 2020 paper "Learning and Evaluating Emotion Lexicons for 91 Languages"☆27Dec 8, 2022Updated 3 years ago
- spaCy pipeline component for adding text readability meta data to Doc objects.☆56Apr 1, 2019Updated 6 years ago