604 Open source projects that are alternatives of or similar to Natasha

Large silver standart Russian corpus with NER, morphology and syntax markup

🇷🇺 Punctuation restoration production-ready model for Russian language 🇷🇺

Compact high quality word embeddings for Russian language

Text2Text: Cross-lingual natural language processing and generation toolkit

xmnlp：提供中文分词, 词性标注, 命名体识别，情感分析，文本纠错，文本转拼音，文本摘要，偏旁部首等功能

fastHan是基于fastNLP与pytorch实现的中文自然语言处理工具，像spacy一样调用方便。

Open Korean Text Processor - An Open-source Korean Text Processor

Classify Kaggle Consumer Finance Complaints into 11 classes. Build the model with CNN (Convolutional Neural Network) and Word Embeddings on Tensorflow.

A tool for learning vector representations of words and entities from Wikipedia

Classify Kaggle San Francisco Crime Description into 39 classes. Build the model with CNN, RNN (GRU and LSTM) and Word Embeddings on Tensorflow.

The smart, automatic Dark Mode toggle for macOS Mojave+

中文 NLP 任务预处理工具包，准确、高效、零使用门槛

한국어 자연어처리를 위한 파이썬 라이브러리입니다. 단어 추출/ 토크나이저 / 품사판별/ 전처리의 기능을 제공합니다.

React documentation website in Russian / Официальная русская версия сайта React

Библия QA это почти 300 страниц обновляемой смеси ответов на вопросы с реальных собеседований на QA, полезных ресурсов и статей, перевода интересного контента с зарубежных ресурсов и агрегации материала с отечественных.

Ekphrasis is a text processing tool, geared towards text from social networks, such as Twitter or Facebook. Ekphrasis performs tokenization, word normalization, word segmentation (for splitting hashtags) and spell correction, using word statistics from 2 big corpora (english Wikipedia, twitter - 330mil english tweets).

Open STT

🌿 NodeJS PHP Parser - extract AST or tokens (PHP5 and PHP7)

An arctic, north-bluish clean and elegant Visual Studio Code theme.

Sublime Text enhanced syntax highlighting for JavaScript ES6/ES7/ES2015/ES2016/ES2017+, Babel, FlowType, React JSX, Styled Components, HTML5, SCSS3, PHP 7, phpDoc, PHPUnit, MQL4. Basic: Git config files.

Compute Sentence Embeddings Fast!

BERT for Multitask Learning

An online book focusing on Go syntax/semantics and runtime related things

🐛 A tool that can speed up linting of php files by running several lint processes at once.

Named Entity Recognition using multilayered bidirectional LSTM

Learning Named Entity Tagger from Domain-Specific Dictionary

基于Pytorch和torchtext的知识图谱深度学习框架。

Library for faster pinned CPU <-> GPU transfer in Pytorch

Search for Go code using syntax trees

CLUENER2020 中文细粒度命名实体识别 Fine Grained Named Entity Recognition

A python library for self-supervised learning on images.

Rad code slides <🏄/>

Nimfa: Nonnegative matrix factorization in Python

a free and open source speech synthesizer for Russian and other languages

专注于可解释的NLP技术 An NLP Toolset With A Focus on Explainable Inference

A proposal for adding a useful pipe operator to JavaScript.

Optimised tokenizer/lexer generator! 🐄 Uses /y for performance. Moo.

Chinese NER(Named Entity Recognition) using BERT(Softmax, CRF, Span)

Fast word vectors with little memory usage in Python

The classical BiLSTM-CRF model implemented in Tensorflow, for sequence labeling tasks. In Vex version, everything is configurable.

Собрание видеозаписей докладов про JavaScript | 2018

Empower Sequence Labeling with Task-Aware Language Model

Petrovich, an inflector for Russian anthroponyms.

Self-contained Japanese Morphological Analyzer written in pure Go

The fast scanner generator for Java™ with full Unicode support

Implementation of the node2vec algorithm.

An arctic, north-bluish clean and elegant Emacs theme.

Jupyter notebooks in Russian. Introduction to Python, basic algorithms and data structures

👑 spaCy building blocks and visualizers for Streamlit apps

YEDDA: A Lightweight Collaborative Text Span Annotation Tool. Code for ACL 2018 Best Demo Paper Nomination.

Rust native ready-to-use NLP pipelines and transformer-based models (BERT, DistilBERT, GPT2,...)

📘 Russian Version: A community-driven Ruby coding style guide.

Natural Language Processing Pipeline - Sentence Splitting, Tokenization, Lemmatization, Part-of-speech Tagging and Dependency Parsing

A Vietnamese natural language processing toolkit (NAACL 2018)

Top 100 Sublime Text plugin! Markdown syntax highlighter for Sublime Text, with extended support for GFM fenced code blocks, with language-specific syntax highlighting. YAML Front Matter. Works with ST2/ST3. Goes great with Assemble.

A small library for converting tokenized PHP source code into XML (and potentially other formats)

Tensorflow solution of NER task Using BiLSTM-CRF model with Google BERT Fine-tuning And private Server services

Snips Python library to extract meaning from text

Curated List of Persian Natural Language Processing and Information Retrieval Tools and Resources

Curated list of 2vec-type embedding models