pltrdy

rouge

A full Python Implementation of the ROUGE Metric (not a wrapper)

files2rouge

Calculating ROUGE score between two files (line-by-line)

OpenNMT-py

Open-Source Neural Machine Translation in PyTorch http://opennmt.net/

extoracle_summarization

Ext-Oracle Summarization: extractive summarization that maximize ROUGE w.r.t. target

public_meetings

A corpus of meetings, with aligned pairs of transcriptions and reports

autoalign

Align then Summarize: Automatic Alignment Methods for Summarization Corpus Creation

pythonrouge

Python implementation for evaluating summarization by ROUGE package

nlp_benchmarking

anon_cnn_dailymail

Scripts to prepare the CNN/DailyMail dataset, to anonymise & un-anonymise it

dotfiles

Helpfull configuration files

pyrouge

A Python wrapper for the ROUGE summarization evaluation package

python-stanford-corenlp

Official Python interface to CoreNLP using a bidirectional server-client interface.

shared_models

tensor2tensor

A library for generalized sequence to sequence models

acceptability-prediction-in-context

alemi_segmentation

Code and data for segmentation experiments.

C99

C99, a domain-independent algorithm for linear text segmentation by Freddy Choi

ConfigArgParse

A drop-in replacement for argparse that allows options to also be set via config files and/or environment variables.

DeepSpeed

DeepSpeed is a deep learning optimization library that makes distributed training easy, efficient, and effective.

easse

Easier Automatic Sentence Simplification Evaluation

encoder-agnostic-adaptation

Encoder-Agnostic Adaptation for Conditional Language Generation

fastdtw

A Python implementation of FastDTW

GNews

A Happy and lightweight Python Package that Provides an API to search for articles on Google News and returns a JSON response.

InferSent

Sentence embeddings (InferSent) and training code for NLI.

lead_sentences

Generate "lead" summaries

pltrdy.github.io

Build a beautiful and simple website in literally minutes. Demo at http://deanattali.com/beautiful-jekyll

pltrdy_py

SentEval

A python tool for evaluating the quality of sentence embeddings.

summarization-datasets

Pre-processing and in some cases downloading of datasets for the paper "Content Selection in Deep Learning Models of Summarization."

textract

extract text from any document. no muss. no fuss.