https://github.com/ramenjuniti/lexrankmmr

LexRank and MMR package for Japanese documents
https://github.com/ramenjuniti/lexrankmmr

golang japanese lexrank maximum-marginal-relevance nlp text-summarization text-summarizer

Last synced: 2 months ago
JSON representation

LexRank and MMR package for Japanese documents

• Host: GitHub
• URL: https://github.com/ramenjuniti/lexrankmmr
• Owner: ramenjuniti
• License: mit
• Created: 2018-11-03T10:50:57.000Z (over 6 years ago)
• Default Branch: master
• Last Pushed: 2019-03-22T13:27:55.000Z (about 6 years ago)
• Last Synced: 2023-07-27T22:32:40.812Z (almost 2 years ago)
• Topics: golang, japanese, lexrank, maximum-marginal-relevance, nlp, text-summarization, text-summarizer
• Language: Go
• Homepage:
• Size: 28.3 KB
• Stars: 0
• Watchers: 0
• Forks: 0
• Open Issues: 1
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# lexrankmmr

[![GoDoc](http://godoc.org/github.com/fabioberger/chrome?status.svg)](https://godoc.org/github.com/ramenjuniti/lexrankmmr)

[![Build Status](https://travis-ci.org/ramenjuniti/lexrankmmr.svg?branch=master)](https://travis-ci.org/ramenjuniti/lexrankmmr)

## Algorithm

[LexRank: Graph-based Lexical Centrality as Salience in Text Summarization](https://www.cs.cmu.edu/afs/cs/project/jair/pub/volume22/erkan04a-html/erkan04a.html)

[The Use of MMR, Diversity-Based Reranking for Reordering Documents and Producing Summaries](http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.188.3982&rep=rep1&type=pdf)

## Dependency

- [github.com/dcadenas/pagerank](https://github.com/dcadenas/pagerank)

- [github.com/gaspiman/cosine_similarity](https://github.com/gaspiman/cosine_similarity)

- [github.com/ikawaha/kagome](https://github.com/ikawaha/kagome)

## install

```sh

go get github.com/ramenjuniti/lexrankmmr

```

## Usage

```go

package main

import github.com/ramenjuniti/lexrankmmr

func main() {

    text := "Please input the document you want to summarize here."

    summary, err := lexrankmmr.New(

        lexrankmmr.MaxLines(maxLines),            // option (default 0)

        lexrankmmr.MaxCharacters(maxCharacters),  // option (default 0)

        lexrankmmr.Threshold(threshold),          // option (default 0.1)

        lexrankmmr.Tolerance(tolerance),          // option (default 0.0001)

        lexrankmmr.Damping(damping),              // option (default 0.85)

        lexrankmmr.Lambda(lambda),                // option (default 1.0)

    )

    err = summary.Summarize(text)

    if err != nil {

        log.Fatal(err)

    }

}

```

## License

This software is released under the MIT License, see LICENSE.