Metadata-Version: 2.1
Name: nlptriples
Version: 0.1.4
Summary: A package to extract Triples in form of [predictate , object , subject]  form text 
License: MIT
Keywords: Poetry,NLP,Triples
Author: adityaparkhi
Author-email: theaditya140@gmail.com
Requires-Python: >=3.6,<4.0
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.6
Classifier: Programming Language :: Python :: 3.7
Classifier: Programming Language :: Python :: 3.8
Requires-Dist: benepar[cpu] (>=0.1.2,<0.2.0)
Requires-Dist: cython (>=0.29.16,<0.30.0)
Requires-Dist: numpy (>=1.18.2,<2.0.0)
Requires-Dist: spacy (>=2.2.4,<3.0.0)
Requires-Dist: tensorflow (==1.15.2)
Description-Content-Type: text/markdown

# NLPTriples
Extract NLP (RDF) Triples from a sentence

# Overview
A minimalistic library to extract triples from sentences. Implemented [paper](http://ailab.ijs.si/dunja/SiKDD2007/Papers/Rusu_Trippels.pdf) 

Converted the [api](https://github.com/tdpetrou/RDF-Triple-API) created by [Ted Petrou](https://github.com/tdpetrou) to a simple library which can be be run directly.

# Installation 
Install using pip

```pip install nlptriples```

# Usage
```python
from nlptriples import triples,setup
rdf = triples.RDF_triple()
triple = rdf.extract(sent)
print(triple)
```

# Imeplemetation
1. Constituency Parse tree is create using Berkeley Neural Parser library. (the paper uses CoreNLP)
2. The algorithm described in the [paper](http://ailab.ijs.si/dunja/SiKDD2007/Papers/Rusu_Trippels.pdf) is used to extract triples from parse trees.

