Skip to main content

Natural Language Generation library for Python

Project description

Current Status build

This is just a starting point - an alpha version - mainly a wrapper around SimpleNLG.

Although it is possible to go from first order logic to text, there is no sophistication in how things are processed. The library is still missing basics like aggregation or referring expression generation.

Installation

Either download the code from the repository and run python setup.py install or use pip: pip install nlglib.

Intro

NLGlib is a library for natural language generation (NLG) written in Python. It seeks to fill a gap in the NLG field. There are currently no off-the-shelf libraries that one could take and incorporate into other projects. The aim of this library is to be useful for general projects that would like to add a bit of text generation to their capabilities.

Audience

The library should be usable by programmers with no prior linguistic knowledge. Given that the aim of the library is language generation, some linguistic knowledge is necessary but you should be able to pick it up from the examples.

Scope

The aim of the library is to create a base for NLG system starting from content selection all the way to realisation. The library will cover document structuring tools, lexicalisation, referring expression generation and aggregation. Realisation will be done using other realisation libraries (SimpleNLG or pynlg).

History

NLGlib started as a part of the EPSRC project Scrutable Autonomous Systems (SAsSy): www.scrutable-systems.org When the project finished, the code was moved to this repository to create a stand-alone re-usable library.

Example

from nlglib.realisation.simplenlg.realisation import Realiser
from nlglib.microplanning import *

realise_en = Realiser(host='nlg.kutlak.info', port=40000)
realise_es = Realiser(host='nlg.kutlak.info', port=40001)


def main():
    p = Clause("María", "perseguir", "un mono")
    p['TENSE'] = 'PAST'
    # expected = 'María persigue un mono.'
    print(realise_es(p))
    p = Clause(NP("la", "rápida", "corredora"), VP("perseguir"), NP("un", "mono"))
    subject = NP("la", "corredora")
    objekt = NP("un", "mono")
    verb = VP("perseguir")
    subject.premodifiers.append("rápida")
    p.subject = subject
    p.predicate = verb
    p.object = objekt
    # expected = 'La rápida corredora persigue un mono.'
    print(realise_es(p))
    p = Clause(NP('this', 'example'), VP('show', 'how cool simplenlg is'))
    # expected = This example shows how cool simplenlg is.
    print(realise_en(p))


if __name__ == '__main__':
    main()

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Files for nlglib, version 0.2.1
Filename, size File type Python version Upload date Hashes
Filename, size nlglib-0.2.1-py3-none-any.whl (3.3 MB) File type Wheel Python version py3 Upload date Hashes View hashes
Filename, size nlglib-0.2.1.tar.gz (55.0 kB) File type Source Python version None Upload date Hashes View hashes

Supported by

Elastic Elastic Search Pingdom Pingdom Monitoring Google Google BigQuery Sentry Sentry Error logging AWS AWS Cloud computing DataDog DataDog Monitoring Fastly Fastly CDN DigiCert DigiCert EV certificate StatusPage StatusPage Status page