285 Open source projects that are alternatives of or similar to Ekphrasis

pyarabic

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

fastNLP: A Modularized and Extensible NLP Framework. Currently still in incubation.

Juman++ (a Morphological Analyzer Toolkit)

A comparison tool of Japanese tokenizers

A Japanese tokenizer based on recurrent neural networks

Thai Natural Language Processing in Python.

The aim of this repository is to show a baseline model for text classification by implementing a LSTM-based model coded in PyTorch. In order to provide a better understanding of the model, it will be used a Tweets dataset provided by Kaggle.

PyNLPl, pronounced as 'pineapple', is a Python library for Natural Language Processing. It contains various modules useful for common, and less common, NLP tasks. PyNLPl can be used for basic tasks such as the extraction of n-grams and frequency lists, and to build simple language model. There are also more complex data types and algorithms. Moreover, there are parsers for file formats common in NLP (e.g. FoLiA/Giza/Moses/ARPA/Timbl/CQL). There are also clients to interface with various NLP specific servers. PyNLPl most notably features a very extensive library for working with FoLiA XML (Format for Linguistic Annotation).

A Python package that do stemming, tokenization, sentence breaking, segmentation, normalization, POS tagging for Arabic language.

Useful python NLP tools (evaluation, GUI interface, tokenization)

Self-contained Japanese Morphological Analyzer written in pure Go

A repository to bind mecab for Python 3.5+. Not using swig nor pybind. (Not Maintained Now)

A foundation for GNU/Linux shell scripting

Python port of Moses tokenizer, truecaser and normalizer

A very simple python tokenizer for Hebrew text.

High performance unsupervised text tokenization for Ruby

A Vietnamese natural language processing toolkit (NAACL 2018)

Pytorch NLP library based on FastAI

A toolkit for Vietnamese word segmentation

使用 PaddlePaddle 实现基于深度神经网络的中文分词引擎 | A DNN Chinese Tokenizer by Using PaddlePaddle

Text2Text: Cross-lingual natural language processing and generation toolkit

Extraction of the five journalistic W-questions (5W) from news articles

TEANAPS 라이브러리를 활용한 자연어 처리와 텍스트 분석 방법론에 대해 다룹니다.

Simple SQL-like syntax on top of Perl text processing.

👄 The most accurate natural language detection library for Java and the JVM, suitable for long and short text alike

A simple interpreter for a large subset of Pascal language written for educational purposes

A modern CSS value compiler in JavaScript

Rakuten MA (Python version)

A multilingual command line sentence tokenizer in Golang

Qiniu Text Processing Libraries for Go

BERT for Multitask Learning

Chinese tokenizer for tantivy, based on jieba-rs

Textpipe: clean and extract metadata from text

🍟 [Library] dA aNn0Y1Ng t3Xt g3NeRa7or

Python port of SymSpell

classy is a simple-to-use library for building high-performance Machine Learning models in NLP.

chatbot_ner: Named Entity Recognition for chatbots.

🗣️ Tool to generate adversarial text examples and test machine learning models against them

Fast SymSpell written in c++ and exposes to python via pybind11

Java port of SymSpell: 1 million times faster through Symmetric Delete spelling correction algorithm

A sharp cut(1) clone.

Simple multilingual lemmatizer for Python, especially useful for speed and efficiency

Hashformers is a framework for hashtag segmentation with transformers.

Lex machinary for go.

Drop-in replacements for base R string functions powered by stringi

🔬 Очистка датасетов от мусора (нормализация, препроцессинг)

Morphological analyzer `mystem` (Russian language) wrapper for JVM languages

基于Tensorflow的中文分词模型

Converts from Chinese characters to pinyin, between simplified and traditional, and does word segmentation.

Library of state-of-the-art models (PyTorch) for NLP tasks

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

A python package to run contextualized topic modeling. CTMs combine BERT with topic models to get coherent topics. Also supports multilingual tasks. Cross-lingual Zero-shot model published at EACL 2021.

🐎 A fast implementation of the Aho-Corasick algorithm using the compact double-array data structure.

Transliterate español (spanish) spelling to andaluz proposals using javascript

Tokenize CSS according to the CSS Syntax

Explaining textual analysis tools in Python. Including Preprocessing, Skip Gram (word2vec), and Topic Modelling.

自然语言处理常见任务（主要包括文本分类，序列标注，自动问答等）解决方案试验田

Extraction of the journalistic five W and one H questions (5W1H) from news articles: who did what, when, where, why, and how?

PowerShell “standard” library for supercharging your productivity. Provides a powerful cross-platform scripting environment enabling efficient analysis and sustainable science in myriad contexts.