193 Open source projects that are alternatives of or similar to Kiwi

Self-contained Japanese Morphological Analyzer written in pure Go

Juman++ (a Morphological Analyzer Toolkit)

Korean sejong corpus download and simple analysis

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).

Unsupervised text tokenizer for Neural Network-based text generation.

The Mobile Application Security Verification Standard (MASVS) is a standard for mobile app security.

Library for Korean morpheme and word vector representation

South Korea administrative divisions in ESRI Shapefile, GeoJSON and TopoJSON formats.

Hangul disasm/asm

A Japanese tokenizer based on recurrent neural networks

IOCP 실습

C++ 핵심 가이드라인 한글화 프로젝트 (C++ Core Guidelines)

🎁 Go By Example 한국어 버전

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

SmartyPants for Korean language

🇰🇷 한국어 사용자를 위한 서비스에 사용하기 위한 오픈 API 모음

[은는이가] 한글 조사(助詞) 대응 I18n engine extension

A Vietnamese natural language processing toolkit (NAACL 2018)

TTS for pitch-accented language. Korean dialect DB.

TUFS Asian Language Parallel Corpus

을유문화사에서 만든 을유1945 폰트를 웹에서 손쉽게 사용할 수 있는 환경을 제공합니다.

TypeScript Handbook in Korean.

zz절대 적용 안하죠?

Modern JavaScript Tutorial in Korean (모던 JavaScript 튜토리얼)

基于Tensorflow的中文分词模型

A tiny JavaScript utility that corrects miswritten Hangeul sentences like gksdud

Thai Natural Language Processing in Python.

Brainfarts are caused by the rupturing of the cerebral sphincter.

🍣 국내 스시 오마카세 맛집 리스트

Rakuten MA (Python version)

Source code for an ACL2016 paper of Chinese word segmentation

A Japanese Tokenizer for Business

🇰🇷 GraphQL Document in Korean

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

A comparison tool of Japanese tokenizers

Python port of SymSpell

HaskellStudy

BERT for Multitask Learning

빠르고 가벼운 전국 초, 중, 고등학교 급식 식단/학사일정 파서

🇰🇷 TypeScript Handbook in Korean

PurePos is an open source hybrid morphological tagger.

Korean analysis plugin that integrates open-korean-text module into elasticsearch.

Joe Speigle's Korean/English dictionary database

Daum 맞춤법 검사기로 텍스트를 보내 손쉽게 교정 가능한 Atom package

Hashformers is a framework for hashtag segmentation with transformers.

Korean grapheme-to-phone conversion in Python

Open Korean NLP Dataset Curation for the Users All Around the Globe

基于隐式马尔可夫模型和正向最大化匹配的中文分词系统

reference code for Rouzeta(FST-based morpological analyzer)

CCXT.NET – CryptoCurrency eXchange Trading Library for .NET

An NLP pipeline for Hebrew

Unsupervised text tokenizer focused on computational efficiency

한글 손글씨 분류 모델을 만들어 iOS 애플리케이션에 적용해보았습니다 📱

Python package for Korean natural language processing.

Korean Visual Question Answering

Let's learn React in Korean!!! (⚛ + 🇰🇷 = 😈 😈 😈)

A hexo plugin that generates a list of links to related posts and popular posts. Also , this plugin can get Visitor Counts (PV) on posts.

Project for segmentation of blood vessels, microaneurysm and hardexudates in fundus images.

Qutuf (قُطُوْف): An Arabic Morphological analyzer and Part-Of-Speech tagger as an Expert System.

Multi-layer Recurrent Neural Networks for character-level language models implements by TensorFlow