A CoNLL-U parser that takes a CoNLL-U formatted string and turns it into a nested python dictionary.

A lexicon for Sudachi

A distributed approximate nearest neighborhood search (ANN) library which provides a high quality vector index build, search and distributed online serving toolkits for large scale vector search sc…

Train emoji embeddings based on emoji descriptions.

emoji2vec: Learning Emoji Representations from their Description

libiconv Windows build with Visual Studio.

Seamless operability between C++11 and Python

Google AI 2018 BERT pytorch implementation

General purpose C++ library for PFI

Lightweight C++ command line option parser

Bidirectional LSTM-CRF and ELMo for Named-Entity Recognition, Part-of-Speech Tagging and so on.

Sequence to Sequence Learning with Keras

Python version of Sudachi, a Japanese tokenizer.

形態素解析器性能評価システム MevAL

A C++11 library for serialization

BlackOut and Adaptive Softmax for language models by Chainer

Various examples for Kotlin

The tool to make NLP datasets ready to use

Fairy Morphological Annotated Corpus

A large parallel corpus of English and Japanese

A clone of Darts (Double-ARray Trie System)

Yet Another Japanese Dependency Structure Analyzer

An open-source NLP research library, built on PyTorch.

💫 Industrial-strength Natural Language Processing (NLP) in Python

A Japanese Tokenizer for Business

これまで研究室の勉強会などで使ってきた資料など

Code accompanying our EMNLP paper Learning Language Representations for Typology Prediction

A Python library to use infix notation in Python

Code for SAILORS 2017 NLP project