Track Awesome Nlg Updates Daily

A curated list of resources dedicated to Natural Language Generation (NLG)

🏠 Home · 🔍 Search · 🔥 Feed · 📮 Subscribe · ❤️ Sponsor · 😺 accelerated-text/awesome-nlg · ⭐ 424 · 🏷️ Computer Science

[ Daily / Weekly / Overview ]

Sep 03, 2023

Neural Natural Language Generation

• lightnlg (⭐3) - A minimalistic codebase for finetuning and interacting with NLG models using PyTorch Lightning.

Feb 03, 2023

Libraries

• Writebot - A NodeJS library that makes it easier to use GPT-3 by using presets.

Mar 23, 2022

Papers and Articles

• 2022: Repairing the Cracked Foundation: A Survey of Obstacles in Evaluation Practices for Generated Text

Apr 16, 2021

Datasets

• WikiBio - wikipedia biography dataset - This dataset gathers 728,321 biographies from wikipedia. It aims at evaluating text generation algorithms.

Mar 25, 2021

Papers and Articles

• 2021: Vision: NLG Can Help Humanise Data and AI

Feb 03, 2021

Evaluation

• GEM - a benchmark environment for NLG with a focus on its Evaluation, both through human annotations and automated Metrics.

Jan 21, 2021

Evaluation

• BLEURT: a Transfer Learning-Based Metric for Natural Language Generation (⭐569)

Papers and Articles

• 2020: The Curious Case of Neural Text Degeneration

Nov 27, 2020

Papers and Articles

• 2020: A Gold Standard Methodology for Evaluating Accuracy in Data-To-Text Systems

Nov 23, 2020

Neural Natural Language Generation

• PaperRobot: Incremental Draft Generation of Scientific Ideas (⭐468) - We present a PaperRobot who performs as an automatic research assistant.

• Question Generation using hugstransformers (⭐981) - Question generation is the task of automatically generating questions from a text paragraph.

Nov 13, 2020

Papers and Articles

• 2020: Evaluating the state-of-the-art of End-to-End Natural Language Generation: The E2E NLG challenge

Jun 16, 2020

Papers and Articles

• 2020: How to generate text: using different decoding methods for language generation with Transformers

• 2020: Natural language generation: The commercial state ofthe art in 2020

• 2020: Turing-NLG: A 17-billion-parameter language model by Microsoft

• 2019: A Closer Look at Recent Results of Verb Selection for Data-to-Text NLG

• 2019: A Personalized Data-to-Text Support Tool for Cancer Patients

• 2019: Controlling Contents in Data-to-Document Generation with Human-Designed Topic Labels

• 2019: Generated Texts Must Be Accurate!

• 2019: Hotel Scribe: Generating High Variation Hotel Descriptions

• 2019: Revisiting Challenges in Data-to-Text Generation with Fact Grounding

• 2017: Survey of the State of the Art in NaturalLanguage Generation: Core tasks, applicationsand evaluation

• 2016: Natural Language Generation enhances human decision-making with uncertain information

May 26, 2020

Neural Natural Language Generation

• This Word Does Not Exist (⭐1k) - This is a project allows people to train a variant of GPT-2 that makes up words, definitions and examples from scratch.

May 21, 2020

Neural Natural Language Generation

• aitextgen (⭐1.8k) - A robust Python tool for text-based AI training and generation using GPT-2.

May 16, 2020

Datasets

• The Schema-Guided Dialogue Dataset (⭐466) - The Schema-Guided Dialogue (SGD) dataset consists of over 20k annotated multi-domain, task-oriented conversations between a human and a virtual assistant.

Apr 26, 2020

Libraries

• Number Words (⭐194) - Convert a number to an approximated text expression: from '0.23' to 'less than a quarter'.

Apr 09, 2020

Products

• RosaeNLG - An open-source library for node.js or client side (browser) execution, based on the Pug template engine, to generate texts in English, French, German and Italian.

Mar 07, 2020

Videos

• Imitation Learning and its Application to Natural Language Generation

Feb 20, 2020

Evaluation

• compare-mt (⭐446) - A tool for holistic analysis of language generations systems.

Jan 17, 2020

Dialog

• Plato (⭐970) - This is the Plato Research Dialogue System, a flexible platform for developing conversational AI agents.

• RNNLG (⭐488) - RNNLG is an open source benchmark toolkit for Natural Language Generation (NLG) in spoken dialogue system application domains.

Jan 11, 2020

Datasets

• Alex Context NLG Dataset (⭐23) - A dataset for NLG in dialogue systems in the public transport information domain.

• Box-score data (⭐105) - This dataset consists of (human-written) NBA basketball game summaries aligned with their corresponding box- and line-scores.

• WeatherGov - Computer-generated weather forecasts from weather.gov (US public forecast), along with corresponding weather data.

• WebNLG (⭐65) - The enriched version of the WebNLG - a resource for evaluating common NLG tasks, including Discourse Ordering, Lexicalization and Referring Expression Generation.

• The Wikipedia company corpus - Company descriptions collected from Wikipedia. The dataset contains semantic representations, short, and long descriptions for 51K companies in English.

Jan 06, 2020

Neural Natural Language Generation

• Texar (⭐2.4k) - Texar is a toolkit aiming to support a broad set of machine learning, especially natural language processing and text generation tasks.

Jan 02, 2020

Datasets

• Neural-Wikipedian (⭐10) - The repository contains the code along with the required corpora that were used in order to build a system that "learns" how to generate English biographies for Semantic Web triples.

Videos

• Data-To-Text: Generating Textual Summaries of Complex Data - Ehud Reiter

Dec 10, 2019

Neural Natural Language Generation

• PPLM (⭐1.1k) - Plug and Play Language Model implementation. Allows to steer topic and attributes of GPT-2 models.

Dec 07, 2019

Dialog

• Chatito (⭐844) - Generate datasets for AI chatbots, NLP tasks, named entity recognition or text classification models using a simple DSL!

Neural Natural Language Generation

• textgenrnn (⭐4.9k) - Easily train your own text-generating neural network of any size and complexity on any text dataset with a few lines of code.

Videos

• Natural Language Generation (Introduction)

• Strata Data Conference | The future of natural language generation: 2017-2027

• The Quest for Automated Story Generation - Mark Riedl

Nov 25, 2019

Libraries

• Cron Expression Descriptor (⭐898) - A .NET library that converts cron expressions into human readable descriptions.

Nov 23, 2019

Realizers

• Genl (⭐22) - Surface realiser (part of a Natural Language Generation system) using Tree Adjoining Grammar.

• JSrealB (⭐20) - A JavaScript bilingual text realizer for web development.

Nov 12, 2019

Neural Natural Language Generation

• graph-2-text (⭐151) - Graph to sequence implemented in Pytorch combining Graph convolutional networks and opennmt-py.

• Transformers (⭐111k) - State-of-the-art Natural Language Processing for TensorFlow 2.0 and PyTorch.

Nov 04, 2019

Datasets

• E2E - This shared task focuses on recent end-to-end (E2E), data-driven NLG methods, which jointly learn sentence planning and surface realisation from non-aligned data.

• YelpNLG - YelpNLG provides resources for natural language generation of restaurant reviews.

Evaluation

• NLG-eval (⭐1.2k) - Evaluation code for various unsupervised automated metrics for Natural Language Generation.

• VizSeq (⭐434) - A Visual Analysis Toolkit for Text Generation Tasks.

Grammar

• GrammaticalFramework - A programming language for multilingual grammar applications.

• CCGweb (⭐6) - A Web platform for parsing and annotation.

Narrative Generation

• Tracery (⭐2.1k) - A story-grammar generation library for JavaScript.

Neural Natural Language Generation

• Image Caption Generator (⭐145) - A Neural Network based generative model for captioning images using Tensorflow.

• Summary Generation From Structured Data (⭐183) - For converting information present in the form of structured data into natural language text.

Products

• Accelerated Text (⭐734) - Automatically generate multiple natural language descriptions of your data varying in wording and structure.

• Twine - An open-source tool for telling interactive, nonlinear stories.

Realizers

• SimpleNLG-EnFr (⭐25) - SimpleNLG-EnFr 1.1 is a bilingual English/French adaption of SimpleNLG v4.2.

Templating Languages

• calyx (⭐60) - A Ruby library for generating text with recursive template grammars.

• nalgene (⭐54) - Natural language generation language.

• StringTemplate - Java template engine (with ports for C##, Objective-C, JavaScript, Scala) for generating source code, web pages, emails, or any other formatted text output.

Nov 03, 2019

Grammar

• CCG Lab (⭐26) - All combinators, common grammar format, parsing to logical form, parameter estimation for probabilistic CCG.

Narrative Generation

• Random Story Generator (⭐62) - Using Natural Language Generation (NLG) to create a random short story.

Oct 29, 2019

Grammar

• OpenCCG (⭐201) - OpenCCG library for parsing and realization with CCG.

• EasyCCG (⭐58) - CCG: All combinators, common grammar format, parsing to logical form, parameter estimation for probabilistic CCG.

Realizers

• SimpleNLG (⭐795) - Java API for Natural Language Generation.

• SimpleNLG DE (⭐16) - German version of SimpleNLG 4.

Oct 22, 2019

Dialog

• NNDIAL (⭐346) - NNDial is an open source toolkit for building end-to-end trainable task-oriented dialogue models.

• TGen (⭐204) - Statistical NLG for spoken dialogue systems.