Awesome NlgA curated list of resources dedicated to Natural Language Generation (NLG)
NumberwordsConvert a number to an approximated text expression: from '0.23' to 'less than a quarter'.
TgenStatistical NLG for spoken dialogue systems
NonautoreggenprogressTracking the progress in non-autoregressive generation (translation, transcription, etc.)
Transformers🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
MojitalkCode for "MojiTalk: Generating Emotional Responses at Scale" https://arxiv.org/abs/1711.04090
Textaugmentation Gpt2Fine-tuned pre-trained GPT2 for custom topic specific text generation. Such system can be used for Text Augmentation.
Dgm latent bowImplementation of NeurIPS 19 paper: Paraphrase Generation with Latent Bag of Words
Gpt2PyTorch Implementation of OpenAI GPT-2
Nlg RlAccelerated Reinforcement Learning for Sentence Generation by Vocabulary Prediction
DipsNAACL 2019: Submodular optimization-based diverse paraphrasing and its effectiveness in data augmentation
Pqg PytorchParaphrase Generation model using pair-wise discriminator loss
Nlg EvalEvaluation code for various unsupervised automated metrics for Natural Language Generation.
SimplenlgJava API for Natural Language Generation. Originally developed by Ehud Reiter at the University of Aberdeen’s Department of Computing Science and co-founder of Arria NLG. This git repo is the official SimpleNLG version.
PplmPlug and Play Language Model implementation. Allows to steer topic and attributes of GPT-2 models.
RnnlgRNNLG is an open source benchmark toolkit for Natural Language Generation (NLG) in spoken dialogue system application domains. It is released by Tsung-Hsien (Shawn) Wen from Cambridge Dialogue Systems Group under Apache License 2.0.
Practical PytorchGo to https://github.com/pytorch/tutorials - this repo is deprecated and no longer maintained
PaperrobotCode for PaperRobot: Incremental Draft Generation of Scientific Ideas
NndialNNDial is an open source toolkit for building end-to-end trainable task-oriented dialogue models. It is released by Tsung-Hsien (Shawn) Wen from Cambridge Dialogue Systems Group under Apache License 2.0.
Accelerated TextAccelerated Text is a no-code natural language generation platform. It will help you construct document plans which define how your data is converted to textual descriptions varying in wording and structure.
Kenlg ReadingReading list for knowledge-enhanced text generation, with a survey
uctfUnsupervised Controllable Text Generation (Applied to text Formalization)
classyclassy is a simple-to-use library for building high-performance Machine Learning models in NLP.
text2textText2Text: Cross-lingual natural language processing and generation toolkit
turingadviceEvaluating Machines by their Real-World Language Use
nlp-notebooksA collection of natural language processing notebooks.
NRCNatural language generation for discrete data in EHRs
Entity2Topic[NAACL2018] Entity Commonsense Representation for Neural Abstractive Summarization
PlanSum[AAAI2021] Unsupervised Opinion Summarization with Content Planning
mtdataA tool that locates, downloads, and extracts machine translation corpora
factedit🧐 Code & Data for Fact-based Text Editing (Iso et al; ACL 2020)
numberwordsConvert a number to an approximated text expression: from '0.23' to 'less than a quarter'.
nlg-markovify-apiAn API built on Plumber (R) utilizing Markovify, a Python package, wrapped in markovifyR (R). It builds a Markov Chain-model based on text (user input) and generates new text based on the model.
TextFeatureSelectionPython library for feature selection for text features. It has filter method, genetic algorithm and TextFeatureSelectionEnsemble for improving text classification models. Helps improve your machine learning models
easseEasier Automatic Sentence Simplification Evaluation
SGCPTACL 2020: Syntax-Guided Controlled Generation of Paraphrases
awesome-nlgA curated list of resources dedicated to Natural Language Generation (NLG)
rtgReader Translator Generator - NMT toolkit based on pytorch
Court-View-GenInterpretable Charge Predictions for Criminal Cases: Learning to Generate Court Views from Fact Descriptions
DCGCNDensely Connected Graph Convolutional Networks for Graph-to-Sequence Learning (authors' MXNet implementation for the TACL19 paper)