All Projects → shimo-lab → sembei

shimo-lab / sembei

Licence: other
🍘 単語分割を経由しない単語埋め込み 🍘

Programming Languages

Jupyter Notebook
11667 projects
python
139335 projects - #7 most used programming language

Projects that are alternatives of or similar to sembei

sentiment-analysis-of-tweets-in-russian
Sentiment analysis of tweets in Russian using Convolutional Neural Networks (CNN) with Word2Vec embeddings.
Stars: ✭ 51 (+264.29%)
Mutual labels:  word-embeddings, computational-linguistics
word2vec-tsne
Google News and Leo Tolstoy: Visualizing Word2Vec Word Embeddings using t-SNE.
Stars: ✭ 59 (+321.43%)
Mutual labels:  word-embeddings, computational-linguistics
datastories-semeval2017-task6
Deep-learning model presented in "DataStories at SemEval-2017 Task 6: Siamese LSTM with Attention for Humorous Text Comparison".
Stars: ✭ 20 (+42.86%)
Mutual labels:  word-embeddings, computational-linguistics
SentimentAnalysis
Sentiment Analysis: Deep Bi-LSTM+attention model
Stars: ✭ 32 (+128.57%)
Mutual labels:  word-embeddings, computational-linguistics
alternativeto
A comprehensive list of alternatives to your favorite software
Stars: ✭ 29 (+107.14%)
Mutual labels:  software
setup shift
📨 Automate the download of your current setup
Stars: ✭ 11 (-21.43%)
Mutual labels:  software
react-toolkit
Flexible components html + css + react using BEM convention. Maybe, you can call it "Design System" !
Stars: ✭ 89 (+535.71%)
Mutual labels:  software
RazerAmbilight
Razer Ambilight - A background process that creates an ambilight effect for razer keyboards.
Stars: ✭ 30 (+114.29%)
Mutual labels:  software
yelp comments classification nlp
Yelp round-10 review comments classification using deep learning (LSTM and CNN) and natural language processing.
Stars: ✭ 72 (+414.29%)
Mutual labels:  word-embeddings
react-native-permissions-modal
Awesome & Fully Customizable Permissions Modal for React Native
Stars: ✭ 26 (+85.71%)
Mutual labels:  software
RMEBuilder
[DEPRECATED] Package Manager (like Aptitude, for Debian) (and project builder) for RPGMaker VXAce
Stars: ✭ 15 (+7.14%)
Mutual labels:  software
Haxe-Macro-Book
Haxeのマクロ本
Stars: ✭ 20 (+42.86%)
Mutual labels:  japanese
Chrome-Dino-Runner
🐱‍🐉 A Replica of the hidden Dinosaur Game from Chrome Browser Offline mode build using Python and PyGame.
Stars: ✭ 22 (+57.14%)
Mutual labels:  software
react-native-imaged-carousel-card
Fully customizable & Lovely Imaged Carousel Card for React Native
Stars: ✭ 70 (+400%)
Mutual labels:  software
unidic-py
Unidic packaged for installation via pip.
Stars: ✭ 17 (+21.43%)
Mutual labels:  japanese
tamagotchi-tech-specs
Tamagotchi Tech Specs
Stars: ✭ 29 (+107.14%)
Mutual labels:  software
awesome-aha
Awesome list for "Aha!" moments related to programming and computer science. Accelerate your learning.
Stars: ✭ 77 (+450%)
Mutual labels:  software
japanese-pitch-accent-resources
Trying to consolidate japanese phonetic, and in particular pitch accent resources into one list
Stars: ✭ 64 (+357.14%)
Mutual labels:  japanese
sample-ui-react
Material-UI+ React.js + Redux [ Pug / Scss / Babel ]
Stars: ✭ 15 (+7.14%)
Mutual labels:  japanese
community-content
Quer contribuir para a comunidade por meio dos canais da BrazilJS e ainda ganhar benefícios legais?
Stars: ✭ 16 (+14.29%)
Mutual labels:  software

oscca-sembei : Segmentation-free version of OSCCA

単語分割を経由しない単語埋め込み手法 segmentation-free word embeddings (sembei) [1] の Python 実装. この実装では,行列分解に基づく単語埋め込み手法 eigenwords (OSCCA) [2] をベースにしている.

Installation

git clone https://github.com/shimo-lab/sembei
cd sembei
python setup.py build && python setup.py install

How to use

./sample_code/ のファイルを参照.

Requirements

  • anaconda3 (>=4.2.0)

References

  1. 押切 孝将, 下平 英寿. 単語分割を経由しない単語埋め込み. 言語処理学会第23回年次大会論文集, pp.258-261. 言語処理学会, 2017年3月.
  2. Dhillon, P. S., Foster, D. P., and Ungar, L. H. (2015). Eigenwords: Spectral word embeddings. Journal of Machine Learning Research, 16:3035–3078.
Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].