ro_sgns

KO | EN

gitlite — search

#ai #llm #android #machine-learning #rust #deep-learning #java #windows #awesome-list #pytorch #security #openai #ios #open-source

(★ 19)

Implementation of Riemannian optimization for skip-gram negative sampling (ACL 2017)

ro_sgns 최신버젼 다운로드

최종 버전 다운로드 (.zip)

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

# Introduction

This repository implements [ACL 2017 Riemannian optimization for skip-gram negative sampling (Fonarev, Hrinchuk et al.)](https://arxiv.org/pdf/1704.08059.pdf).
```
@inproceedings{fonarev2017ro_sgns,
  title={Riemannian Optimization for Skip-Gram Negative Sampling},
  author={Alexander Fonarev and Oleksii Hrinchuk and Gleb Gusev and Pavel Serdyukov and Ivan Oseledets},
  booktitle={ACL},
  year={2017}
}
```

# Prerequisits

- [numpy](http://www.numpy.org)
- [scipy](https://www.scipy.org)
- [pandas](https://pandas.pydata.org)
- [gensim](https://radimrehurek.com/gensim/)
- [nltk](https://www.nltk.org)
- [bs4](https://www.crummy.com/software/BeautifulSoup/bs4/doc/)

```
pip install numpy scipy pandas gensim nltk bs4 
```

# Usage

- Clone **ro_sgns** repostirtory:

```
git clone https://github.com/AlexGrinch/ro_sgns.git
cd ro_sgns
```

- Download [enwik9](http://mattmahoney.net/dc/enwik9.zip) dataset and preprocess raw data with Perl script [main_.pl](main_.pl).

```
wget http://mattmahoney.net/dc/enwik9.zip
unzip enwik9.zip
mkdir data
perl main_.pl enwik9 > data/enwik9.txt
```

- Run IPython notebook [enwik_experiments.ipynb](enwik_experiments.ipynb).

```
jupyter notebook enwik_experiments.ipynb
```

# Algorithm

|![algorithm](https://raw.githubusercontent.com/AlexGrinch/ro_sgns/master/img/algorithm.png) | ![geometric](https://raw.githubusercontent.com/AlexGrinch/ro_sgns/master/img/ro.png)
|:---:|:---:|
|**Figure 1.** Riemannian optimization for skip-gram negative sampling (RO-SGNS) algorithm. | **Figure 2.** Geometric interpretation of one step of Riemannain optimization procedure: the point is first projected onto the tangent space and then retracted to the manifold.|

# Results

|![corr](https://raw.githubusercontent.com/AlexGrinch/ro_sgns/master/img/corr_results.png) | ![neighbors](https://raw.githubusercontent.com/AlexGrinch/ro_sgns/master/img/neighbors_results.png)
|:---:|:---:|
|**Table 1.** Spearman’s correlation between predicted similarities and the manually assesed ones. | **Table 2.** Examples of the semantic neighbors (in terms of cosine similarity) for the word <b>usa</b>.|

ro_sgns

ro_sgns 최신버젼 다운로드

오늘의 추천 프로젝트

Was this content helpful?

Recent Feedback

ro_sgns

ro_sgns 최신버젼 다운로드

오늘의 추천 프로젝트

Was this content helpful?

Recent Feedback

Download README