Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Juman++ (a Morphological Analyzer Toolkit)
| Date | Stars |
|---|---|
| 2026-07-24 | 414 |
| 2026-07-25 | 414 |
| 2026-07-28 | 414 |
| 2026-07-30 | 414 |
| 2026-08-06 | 414 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# What is Juman++
A new morphological analyser that considers semantic plausibility of
word sequences by using a recurrent neural network language model (RNNLM).
Version 2 has better accuracy and greatly (>250x) improved analysis speed than
the original Juman++.
[](https://github.com/ku-nlp/jumanpp/actions/workflows/cmake.yml)
# Installation
## System Requirements
* OS: Linux, MacOS X or Windows.
* Compiler: C++14 compatible
* For example gcc 5.1+, clang 3.4+, MSVC 2017
* We test on GCC and clang on Linux/MacOS, mingw64-gcc and MSVC2017 on Windows
- CMake v3.13 or later
- For Ubuntu22.04, you need to install additional packages as follows: `sudo apt install libprotobuf-dev protobuf-compiler`
Read [this document](docs/building.md) for CentOS and RHEL derivatives or non-CMake alternatives.
## Building from a package
Download the package from [Releases](https://github.com/ku-nlp/jumanpp/releases)
**Important**: The download should be around 300 MB. If it is not you have probably downloaded a source snapshot which does not contain a model.
```bash
$ tar xf jumanpp-<version>.tar.xz # decompress the package
$ cd jumanpp-<version>
$ cmake -S . -B build \
-DCMAKE_BUILD_TYPE=Release \
-DCMAKE_INSTALL_PREFIX=<prefix>
$ cmake --build build -j<parallelism>
$ cmake --install build
```
## Building from git
**Important**: Only the package distribution contains a pretrained model and can be used for analysis.
The current git version is not compatible with the models of 2.0-rc1 and 2.0-rc2.
```bash
$ cmake -S . -B build
$ cmake --build build -j
```
# Usage
## Quick start
```
% echo "魅力がたっぷりと詰まっている" | jumanpp
魅力 みりょく 魅力 名詞 6 普通名詞 1 * 0 * 0 "代表表記:魅力/みりょく カテゴリ:抽象物"
が が が 助詞 9 格助詞 1 * 0 * 0 NIL
たっぷり たっぷり たっぷり 副詞 8 * 0 * 0 * 0 "自動認識"
と と と 助詞 9 格助詞 1 * 0 * 0 NIL
詰まって つまって 詰まる 動詞 2 * 0 子音動詞ラ行 10 タ系連用テ形 14 "代表表記:詰まる/つまる ドメイン:料理・食事 自他動詞:他:詰める/つめる"
いる いる いる 接尾辞 14 動詞性接尾辞 7 母音動詞 1 基本形 2 "代表表記:いる/いる"
EOS
```
## Main options
```
usage: jumanpp [options]
-s, --specifics lattice format output (unsigned int [=5])
--beam <int> set local beam width used in analysis (unsigned int [=5])
-v, --version print version
-h, --help print this message
--model <file> specify a model location
```
Use `--help` to see more options.
## Input
JUMAN++ can handle only utf-8 encoded text as an input.
Lines beginning with `# ` will be interpreted as comments.
## Training Jumandic Model
A set of scripts for training Jumandic model is available in [this repository](https://github.com/ku-nlp/jumanpp-jumandic).
It is possible to modify the system dictionary to add other entries to the trained model.
**Attention**: You need to have access to Mainichi Shinbun for Year 1995 to be able to use Kyoto Univeristy corpus for training.
# Other
## DEMO
You can play around our [web demo](https://tulip.kuee.kyoto-u.ac.jp/demo/jumanpp_lattice?text=%E5%A4%96%E5%9B%BD%E4%BA%BA%E5%8F%82%E6%94%BF%E6%A8%A9%E3%81%AB%E5%AF%BE%E3%81%99%E3%82%8B%E8%80%83%E3%81%88%E6%96%B9%E3%81%AE%E9%81%95%E3%81%84)
which displays a subset of the whole lattice.
The demo still uses v1 but, it will be updated to v2 soon.
## Extracting diffs caused by beam configurations
You can see sentences in which two different beam configurations produce different analyses.
A `src/jumandic/jpp_jumandic_pathdiff` binary [(source)](https://github.com/ku-nlp/jumanpp/blob/master/src/jumandic/main/path_diff.cc)
(relative to a compilation root) does it.
The only Jumandic-specific thing here is the usage of [code-generated linear model inference](https://github.com/ku-nlp/jumanpp/blob/master/src/jumandic/main/path_diff.cc#L195).
Use the binary as `jpp_jumandic_pathdiff <model> <input> > <output>`.
Outputs would be in the partial annotation format with a full beam results being the actual tags and trimmed beam results being written Excerpt of 7,675 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:c91b57f00c2c3214, topic:nlp, topic:tokenizer