gse

Go efficient multilingual NLP and text segmentation; support English, Chinese, Japanese and others. And supports with elasticsearch and bleve.

简体中文

Gse is implements jieba by golang, and try add NLP support and more feature

Feature:

Support common, search engine, full mode, precise mode and HMM mode multiple word segmentation modes;
Support user and embed dictionary, Part-of-speech/POS tagging, analyze segment info, stop and trim words
Support multilingual: English, Chinese, Japanese and others
Support Traditional Chinese
Support HMM cut text use Viterbi algorithm
Support NLP by TensorFlow (in work)
Named Entity Recognition (in work)
Supports with elasticsearch and bleve
run JSON RPC service.

Algorithm:

Dictionary with double array trie (Double-Array Trie) to achieve
Segmenter algorithm is the shortest path (based on word frequency and dynamic programming), and DAG and HMM algorithm word segmentation.

Text Segmentation speed:

single thread 9.2MB/s
goroutines concurrent 26.8MB/s.
HMM text segmentation single thread 3.2MB/s. (2core 4threads Macbook Pro).

Binding:

gse-bind, binding JavaScript and other, support more language.

Install / update

With Go module support (Go 1.11+), just import:

import "github.com/go-ego/gse"

Otherwise, to install the gse package, run the command:

go get -u github.com/go-ego/gse

Use

package main

import (
	"fmt"
	"regexp"

	"github.com/go-ego/gse"
	"github.com/go-ego/gse/hmm/pos"
)

var (
	text = "Hello world, Helloworld. Winter is coming! こんにちは世界, 你好世界."

	new, _ = gse.New("zh,testdata/test_dict3.txt", "alpha")

	seg gse.Segmenter
	posSeg pos.Segmenter
)

func main() {
	// Loading the default dictionary
	seg.LoadDict()
	// Loading the default dictionary with embed
	// seg.LoadDictEmbed()
	// 
	// Loading the Simplified Chinese dictionary
	// seg.LoadDict("zh_s")
	// seg.LoadDictEmbed("zh_s")
	//
	// Loading the Traditional Chinese dictionary
	// seg.LoadDict("zh_t")
	// 
	// Loading the Japanese dictionary
	// seg.LoadDict("jp")
	// 
	// Load the dictionary
	// seg.LoadDict("your gopath"+"/src/github.com/go-ego/gse/data/dict/dictionary.txt")

	cut()

	segCut()
}

func cut() {
	hmm := new.Cut(text, true)
	fmt.Println("cut use hmm: ", hmm)

	hmm = new.CutSearch(text, true)
	fmt.Println("cut search use hmm: ", hmm)
	fmt.Println("analyze: ", new.Analyze(hmm, text))

	hmm = new.CutAll(text)
	fmt.Println("cut all: ", hmm)

	reg := regexp.MustCompile(`(\d+年|\d+月|\d+日|[\p{Latin}]+|[\p{Hangul}]+|\d+\.\d+|[a-zA-Z0-9]+)`)
	text1 := `헬로월드 헬로 서울, 2021年09月10日, 3.14`
	hmm = seg.CutDAG(text1, reg)
	fmt.Println("Cut with hmm and regexp: ", hmm, hmm[0], hmm[6])
}

func analyzeAndTrim(cut []string) {
	a := seg.Analyze(cut, "")
	fmt.Println("analyze the segment: ", a)

	cut = seg.Trim(cut)
	fmt.Println("cut all: ", cut)

	fmt.Println(seg.String(text, true))
	fmt.Println(seg.Slice(text, true))
}

func cutPos() {
	po := seg.Pos(text, true)
	fmt.Println("pos: ", po)
	po = seg.TrimPos(po)
	fmt.Println("trim pos: ", po)

	pos.WithGse(seg)
	po = posSeg.Cut(text, true)
	fmt.Println("pos: ", po)

	po = posSeg.TrimWithPos(po, "zg")
	fmt.Println("trim pos: ", po)
}

func segCut() {
	// Text Segmentation
	tb := []byte(text)
	fmt.Println(seg.String(text, true))

	segments := seg.Segment(tb)
	// Handle word segmentation results, search mode
	fmt.Println(gse.ToString(segments, true))
}

Look at an custom dictionary example

package main

import (
	"fmt"
	_ "embed"

	"github.com/go-ego/gse"
)

//go:embed test_dict3.txt
var testDict string

func main() {
	// var seg gse.Segmenter
	// seg.LoadDict("zh, testdata/test_dict.txt, testdata/test_dict1.txt")
	// seg.LoadStop()
	seg, err := gse.NewEmbed("zh, word 20 n"+testDict, "en")
	// seg.LoadDictEmbed()
	seg.LoadStopEmbed()

	text1 := "Hello world, こんにちは世界, 你好世界!"
	s1 := seg.Cut(text1, true)
	fmt.Println(s1)
	fmt.Println("trim: ", seg.Trim(s1))
	fmt.Println("stop: ", seg.Stop(s1))
	fmt.Println(seg.String(text1, true))

	segments := seg.Segment([]byte(text1))
	fmt.Println(gse.ToString(segments))
}