ulysses-camara / ulysses-segmenter
Pretrained segmenter models for Portuguese legislative text.
☆14Updated 5 months ago
Alternatives and similar repositories for ulysses-segmenter:
Users that are interested in ulysses-segmenter are comparing it to the libraries listed below
- FaQuAD reading comprehension dataset and related code to reproduce experiments from Sayama et al. (BRACIS 2019).☆8Updated 2 years ago
- Converter from UD-trees to BART representation☆36Updated last year
- ☆17Updated last year
- A small repository to test Captum Explainable AI with a trained Flair transformers-based text classifier.☆27Updated 3 years ago
- ☆19Updated 2 years ago
- SemClinBr - a multi-institutional and multi-specialty semantically annotated corpus for Portuguese clinical NLP tasks☆27Updated last year
- Minimal code to train ELMo models in recent versions of TensorFlow☆14Updated last year
- A python module to process data for Frame Semantic Parsing☆24Updated 4 years ago
- Finds linguistic patterns effortlessly☆35Updated last year
- Tool for parsing and converting various span encoding schemes.☆23Updated last year
- Transformer model for Portuguese language (Brazil pt_BR)☆15Updated 11 months ago
- BERT models for many languages created from Wikipedia texts☆33Updated 4 years ago
- GC4LM: A Colossal (Biased) language model for German☆13Updated 3 years ago
- Code for equipping pretrained language models (BART, GPT-2, XLNet) with commonsense knowledge for generating implicit knowledge statement…☆16Updated 3 years ago
- A set of methods for finding an appropriate number of topics in a text collection☆15Updated last week
- Code for training and evaluating T5 on Portuguese data.☆86Updated 2 years ago
- Preprocessing and analysis for training SNOMED-CT concept embeddings from CORD-19 corpus☆14Updated last year
- sequence tagging with spaCy and crfsuite☆19Updated 2 years ago
- Combining encoder-based language models☆11Updated 3 years ago
- ☆23Updated last year
- Ensemble topic modeling with matrix factorization☆25Updated 6 years ago
- Crawling engine that crawls a set of top-level domains looking for documents in a list of languages☆10Updated last year
- Keras Implementation of Flair's Contextualized Embeddings☆27Updated 3 years ago
- Tokenization across languages. Useful as preprocessing for subword tokenization.☆22Updated 2 years ago
- A curated list of Natural Language Generation papers, tutorials, and blogs.☆12Updated 6 years ago
- ☆21Updated 2 months ago
- Implementation of Nested Named Entity Recognition using Flair☆24Updated 3 years ago
- The Potsdam Twitter Sentiment Corpus☆17Updated 5 years ago
- Tool for the Automatic Assessment of Lexical Diversity☆11Updated 4 years ago
- This repository includes all the code and data for the paper ELiDi (End2end Entity Linking and Disambiguation)☆14Updated 3 years ago