unicamp-dl / PTT5Links
Code for training and evaluating T5 on Portuguese data.
☆90Updated 2 years ago
Alternatives and similar repositories for PTT5
Users that are interested in PTT5 are comparing it to the libraries listed below
Sorting:
- Transformer model for Portuguese language (Brazil pt_BR)☆16Updated last week
- Portuguese translation of the GLUE benchmark and Scitail dataset☆31Updated 3 years ago
- Portuguese Named Entity Recognition☆60Updated last year
- Deep Learning experiments☆19Updated 5 years ago
- The Natural Portuguese Language Benchmark (Napolab). Stay up to date with the latest advancements in Portuguese language models and their…☆70Updated last month
- Portuguese translation of the SQuAD dataset☆19Updated 4 years ago
- ☆21Updated 6 years ago
- SemClinBr - a multi-institutional and multi-specialty semantically annotated corpus for Portuguese clinical NLP tasks☆30Updated last year
- Portuguese BERT and XLM-R models fine-tuned in semantic role labeling.☆25Updated 3 years ago
- ☆11Updated last year
- Evaluation and baseline scripts for the ASSIN shared task.☆11Updated 5 years ago
- Essay-BR: a corpus of essays for the Brazilian Portuguese language☆20Updated 3 years ago
- pt-BR Corpus with the Wikipedia dump☆27Updated 5 years ago
- Python-based implementation of the Translate-Align-Retrieve method to automatically translate the SQuAD Dataset to Spanish.☆59Updated 2 years ago
- ☆16Updated 5 years ago
- ☆28Updated last year
- Biomedical and Clinical BERT for Portuguese Language☆57Updated 9 months ago
- A Hierarchically-Labeled Portuguese Hate Speech Dataset☆33Updated 6 years ago
- Sentence transformers models for SpaCy☆107Updated 2 years ago
- ☆55Updated 2 years ago
- Supporting code for the paper "Portuguese Language Models and Word Embeddings: Evaluating on Semantic Similarity Tasks".☆11Updated 2 years ago
- Hashformers is a framework for hashtag segmentation with Transformers and Large Language Models (LLMs).☆73Updated last year
- A flexible normalizer for user-generated content☆63Updated last week
- HateBR is the first large-scale expert annotated dataset of Brazilian Instagram comments for hate speech and offensive language detection…☆35Updated 2 months ago
- This Universal Dependencies (UD) Portuguese treebank.☆52Updated 2 weeks ago
- LASER multilingual sentence embeddings as a pip package☆224Updated 2 years ago
- Augmenty is an augmentation library based on spaCy for augmenting texts.☆156Updated last year
- A library to synthesize text datasets using Large Language Models (LLM)☆152Updated 2 years ago
- Code and models used in "MUSS Multilingual Unsupervised Sentence Simplification by Mining Paraphrases".☆99Updated 2 years ago
- Main repository for "CharacterBERT: Reconciling ELMo and BERT for Word-Level Open-Vocabulary Representations From Characters"☆201Updated last year