neural-punctuator
Punctuation restorer
An implementation of BERT-based models for automatic punctuation restoration in English and Hungarian texts.
Complimentary code for our paper Automatic punctuation restoration with BERT models
48 stars
4 watching
7 forks
Language: Jupyter Notebook
last commit: almost 3 years agoLinked from 1 awesome list
bertpunctuation-restorationtransformer
oroszgy/awesome-hungarian-nlpRelated projects:
| Repository | Description | Stars |
|---|---|---|
 geyang/deep-auto-punctuation | This project trains an AI model to automatically punctuate text by reading and learning from a specific dataset of English articles. | 141 |
 alvenirai/punctfix | A Python library that adds punctuation and capitalization to text without punctuation. | 23 |
 juditacs/hunaccent | A C++ library that uses machine learning to restore diacritics in Hungarian text | 15 |
 aielte-research/diacritics_restoration | A Python-based framework for training and evaluating diacritics restoration models using lightweight 1D convolutional neural networks | 4 |
 deeppavlov/slavic-bert-ner | A shared BERT model for NER tasks in Slavic languages, pre-trained on Bulgarian, Czech, Polish, and Russian texts. | 73 |
 zhendongwang6/uformer | An implementation of a deep learning model for restoring images in various conditions | 817 |
 swz30/restormer | Proposes an efficient neural architecture model for high-resolution image restoration tasks | 1,845 |
 tonianelope/multilingual-bert | Investigating multilingual language models for Named Entity Recognition in German and English | 14 |
 allegro/herbert | A BERT-based language model pre-trained on Polish corpora for understanding Polish language. | 65 |
 dbmdz/berts | Provides pre-trained language models for natural language processing tasks | 155 |
 laurentmazare/ocaml-bert | Implementing BERT-like NLP models in OCaml using PyTorch bindings and pre-trained weights from popular sources. | 24 |
 yxuansu/tacl | Improves pre-trained language models by encouraging an isotropic and discriminative distribution of token representations. | 92 |
 algolzw/daclip-uir | This project controls vision-language models to restore degraded images in various environments and conditions. | 673 |
 sinovation/zen | A pre-trained BERT-based Chinese text encoder with enhanced N-gram representations | 645 |
 psharanda/atributika | A library that converts HTML-like text into NSAttributedString with various styles and tags | 1,460 |