Skip to content
/ wego Public
forked from ynqa/wego

Word2Vec, GloVe, and Lexvec in Go!

License

Notifications You must be signed in to change notification settings

dormael/wego

This branch is 42 commits behind ynqa/wego:master.

Folders and files

NameName
Last commit message
Last commit date

Latest commit

bbae3aa Β· Dec 26, 2019
Dec 26, 2019
Dec 26, 2019
Dec 26, 2019
Dec 26, 2019
Dec 26, 2019
Aug 16, 2018
Feb 6, 2019
Dec 26, 2019
Dec 26, 2019
Dec 26, 2019
Dec 26, 2019
Dec 26, 2019
Dec 26, 2019
Dec 26, 2019
Dec 26, 2019

Repository files navigation

Word Embedding in Go

Build Status GoDoc Go Report Card

wego is the implementations for word embedding (a.k.a word representation) models in Go. Word embedding makes word's meaning, structure, and concept mapping into vector space with low dimension. For representative instance:

Vector("King") - Vector("Man") + Vector("Woman") = Vector("Queen")

Like this example, models generate word vectors that could calculate word meaning by arithmetic operations for other vectors. wego provides CLI that includes not only training model for embedding but also similarity search between words.

Models

πŸŽƒ Word2Vec: Distributed Representations of Words and Phrases and their Compositionality [pdf]

πŸŽƒ GloVe: Global Vectors for Word Representation [pdf]

πŸŽƒ LexVec: Matrix Factorization using Window Sampling and Negative Sampling for Improved Word Representations [pdf]

Why Go?

Data Science in Go @chewxy

Installation

$ go get -u github.com/ynqa/wego
$ bin/wego -h

Demo

Run the following command, and start to download text8 corpus and train them by Word2Vec.

$ sh scripts/demo.sh

Usage

Usage:
  wego [flags]
  wego [command]

Available Commands:
  glove       GloVe: Global Vectors for Word Representation
  help        Help about any command
  lexvec      Lexvec: Matrix Factorization using Window Sampling and Negative Sampling for Improved Word Representations
  repl        Search similar words with REPL mode
  search      Search similar words
  word2vec    Word2Vec: Continuous Bag-of-Words and Skip-gram model

Flags:
  -h, --help   help for wego

File I/O

Input

Input corpus requires the format that is divided by space between words like text8 since wego parse with scanner.Split(bufio.ScanWords).

Output

Wego outputs a .txt file that is described word vector is subject to the following format:

<word> <value1> <value2> ...

Example

It's also able to train word vectors using wego APIs. Examples are as follows.

package main

import (
	"os"

	"github.com/ynqa/wego/pkg/builder"
	"github.com/ynqa/wego/pkg/model/word2vec"
)

func main() {
	b := builder.NewWord2vecBuilder()

	b.Dimension(10).
		Window(5).
		Model(word2vec.CBOW).
		Optimizer(word2vec.NEGATIVE_SAMPLING).
		NegativeSampleSize(5).
		Verbose()

	m, err := b.Build()
	if err != nil {
		// Failed to build word2vec.
	}

	input, _ := os.Open("text8")

	// Start to Train.
	if err = m.Train(input); err != nil {
		// Failed to train by word2vec.
	}

	// Save word vectors to a text file.
	m.Save("example.txt")
}

About

Word2Vec, GloVe, and Lexvec in Go!

Resources

License

Code of conduct

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Go 96.6%
  • Shell 3.1%
  • Dockerfile 0.3%