poincare-embedding - GitLite

KO | EN

gitlite — search

#javascript #python #typescript #llm #go #android #machine-learning #deep-learning #docker #nodejs #macos #awesome #kubernetes #open-source

poincare-embedding

(★ 229)

Poincaré Embedding (unofficial)

File Explorer

Download Latest Version (.zip)

- poincare_embedding.hpp
- mammal.png
- create_mammal_subtree.py
- create_wordnet_noun_hierarchy.py
- plot_mammal_subtree.py
- plot_tree.py
- rank_norm.py
- poincare_embedding.cpp
.gitignore
CMakeLists.txt
LICENSE
README.md
requirements.txt

# Installation Guide

1. Get the code

git clone https://github.com/TatsuyaShirakawa/poincare-embedding

Downloads the entire project code from GitHub to your computer.

cd poincare-embedding

Moves into the project folder you just downloaded.

2. CMake

Medium Recommended

Prerequisites

Git Needed to download the project code from GitHub.
CMake The tool used to generate build configuration.
C/C++ 컴파일러 Windows needs Visual Studio (Community edition, free), macOS needs Xcode Command Line Tools, Linux needs the gcc/g++ package.

cmake ..

Analyzes the source code and generates build configuration files (must be run inside the build folder).

- for Windows user, using cygwin is recommended (with CMAKE and gcc/g++ selection) (thanks @patrickgitacc)

Type this command into your terminal and run it.

✅ Check that an executable was created inside the build folder, then run it directly (e.g. ./build/app_name).

Pulled directly from this repo's README.

3. Python

Easy

Prerequisites

Git Needed to download the project code from GitHub.
Python 3 On Windows, be sure to check 'Add Python to PATH' during installation.

python3 -m venv venv

Runs the Python script (or module).

python3 -m pip install -r requirements.txt

Installs the Python libraries listed in requirements.txt (or similar).

✅ If it runs without errors and prints output in the terminal, it worked.

Pulled directly from this repo's README.

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

# poincare-embedding

These codes implement Poincar\'e Embedding introduced in the following paper:

[Maximilian Nickel and Douwe Kiela, "Poincar\'e Embeddings for Learning Hierarchical Representations'", arXiv preprint arXiv:1705.08039, 2017.](https://arxiv.org/abs/1705.08039)

## Requirements

- C++ compiler that supports c++14 or later
    - for Windows user, using cygwin is recommended (with CMAKE and gcc/g++ selection) (thanks @patrickgitacc)

## Build

```shell
cd poincare-embedding
mkdir work & cd work
cmake ..
make
```

## Setup python environment

From the poincare-embeddings directory...

```shell
python3 -m venv venv
source venv/bin/activate
```

if using windows:

```shell
python3 -m venv venv
venv\Scripts\activate
```

Then run the following:

```shell
python3 -m pip install -r requirements.txt
python3 -c "import nltk; nltk.download('wordnet')"
```

## Tutorial

We assume that you are in work directory

```shell
cd poincare-embedding
mkdir work & cd work
```

### Data Creation

You can create WordNet noun hypernym pairs as follows

```shell
python ../scripts/create_wordnet_noun_hierarchy.py ./wordnet_noun_hypernyms.tsv
```

and mammal subtree is created by

```shell
python ../scripts/create_mammal_subtree.py ./mammal_subtree.tsv
```

### Run

```shell
./poincare_embedding ./mammal_subtree.tsv ./embeddings.tsv -d 2 -t 8 -e 1000 -l 0.1 -L 0.0001 -n 20 -s 0
```
### Plot a Mammal Tree

```shell
python ../scripts/plot_mammal_subtree.py ./embeddings.tsv --center_mammal
```

Note: if that doesn't work, may need to run the following:

```shell
tr -d '\015' < embeddings.tsv > embeddings_clean.tsv
```

Double check that the file has removed the character in question, then run

```shell
mv embeddings_clean.tsv embeddings.tsv
```

![mammal.png](https://raw.githubusercontent.com/TatsuyaShirakawa/poincare-embedding/master/misc/mammal.png)