1 line
No EOL
15 KiB
JSON
1 line
No EOL
15 KiB
JSON
{"slug": "accelerated-text--awesome-nlg", "title": "Nlg", "description": "A curated list of resources dedicated to Natural Language Generation (NLG)", "github_url": "https://github.com/accelerated-text/awesome-nlg", "stars": "424", "tag": "Computer Science", "entry_count": 86, "subcategory_count": 1, "subcategories": [{"name": "General", "parent": "", "entries": [{"name": "Datasets", "url": "#datasets", "description": ""}, {"name": "Dialog", "url": "#dialog", "description": ""}, {"name": "Evaluation", "url": "#evaluation", "description": ""}, {"name": "Grammar", "url": "#grammar", "description": ""}, {"name": "Libraries", "url": "#libraries", "description": ""}, {"name": "Narrative Generation", "url": "#narrative-generation", "description": ""}, {"name": "Neural Natural Language Generation", "url": "#neural-natural-language-generation", "description": ""}, {"name": "Papers and Articles", "url": "#papers-and-articles", "description": ""}, {"name": "Products", "url": "#products", "description": ""}, {"name": "Realizers", "url": "#realizers", "description": ""}, {"name": "Templating Languages", "url": "#templating-languages", "description": ""}, {"name": "Videos", "url": "#videos", "description": ""}, {"name": "Alex Context NLG Dataset", "url": "https://github.com/UFAL-DSG/alex_context_nlg_dataset", "description": "A dataset for NLG in dialogue systems in the public transport information domain.", "stars": "23"}, {"name": "Box-score data", "url": "https://github.com/harvardnlp/boxscore-data/", "description": "This dataset consists of (human-written) NBA basketball game summaries aligned with their corresponding box- and line-scores.", "stars": "105"}, {"name": "E2E", "url": "http://www.macs.hw.ac.uk/InteractionLab/E2E", "description": "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."}, {"name": "Neural-Wikipedian", "url": "https://github.com/pvougiou/Neural-Wikipedian", "description": "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.", "stars": "10"}, {"name": "WeatherGov", "url": "https://cs.stanford.edu/~pliang/data/weather-data.zip", "description": "Computer-generated weather forecasts from weather.gov (US public forecast), along with corresponding weather data."}, {"name": "WebNLG", "url": "https://github.com/ThiagoCF05/webnlg", "description": "The enriched version of the WebNLG - a resource for evaluating common NLG tasks, including Discourse Ordering, Lexicalization and Referring Expression Generation.", "stars": "65"}, {"name": "WikiBio - wikipedia biography dataset", "url": "https://rlebret.github.io/wikipedia-biography-dataset/", "description": "This dataset gathers 728,321 biographies from wikipedia. It aims at evaluating text generation algorithms."}, {"name": "The Schema-Guided Dialogue Dataset", "url": "https://github.com/google-research-datasets/dstc8-schema-guided-dialogue", "description": "The Schema-Guided Dialogue (SGD) dataset consists of over 20k annotated multi-domain, task-oriented conversations between a human and a virtual assistant.", "stars": "466"}, {"name": "The Wikipedia company corpus", "url": "https://gricad-gitlab.univ-grenoble-alpes.fr/getalp/wikipediacompanycorpus", "description": "Company descriptions collected from Wikipedia. The dataset contains semantic representations, short, and long descriptions for 51K companies in English."}, {"name": "YelpNLG", "url": "https://nlds.soe.ucsc.edu/yelpnlg", "description": "YelpNLG provides resources for natural language generation of restaurant reviews."}, {"name": "Chatito", "url": "https://github.com/rodrigopivi/Chatito", "description": "Generate datasets for AI chatbots, NLP tasks, named entity recognition or text classification models using a simple DSL!", "stars": "844"}, {"name": "NNDIAL", "url": "https://github.com/shawnwun/NNDIAL", "description": "NNDial is an open source toolkit for building end-to-end trainable task-oriented dialogue models.", "stars": "346"}, {"name": "Plato", "url": "https://github.com/uber-research/plato-research-dialogue-system", "description": "This is the Plato Research Dialogue System, a flexible platform for developing conversational AI agents.", "stars": "970"}, {"name": "RNNLG", "url": "https://github.com/shawnwun/RNNLG", "description": "RNNLG is an open source benchmark toolkit for Natural Language Generation (NLG) in spoken dialogue system application domains.", "stars": "488"}, {"name": "TGen", "url": "https://github.com/UFAL-DSG/tgen", "description": "Statistical NLG for spoken dialogue systems.", "stars": "204"}, {"name": "BLEURT: a Transfer Learning-Based Metric for Natural Language Generation", "url": "https://github.com/google-research/bleurt", "description": "", "stars": "569"}, {"name": "compare-mt", "url": "https://github.com/neulab/compare-mt", "description": "A tool for holistic analysis of language generations systems.", "stars": "446"}, {"name": "GEM", "url": "https://gem-benchmark.com/", "description": "a benchmark environment for NLG with a focus on its Evaluation, both through human annotations and automated Metrics."}, {"name": "NLG-eval", "url": "https://github.com/Maluuba/nlg-eval", "description": "Evaluation code for various unsupervised automated metrics for Natural Language Generation.", "stars": "1.2k"}, {"name": "VizSeq", "url": "https://github.com/facebookresearch/vizseq", "description": "A Visual Analysis Toolkit for Text Generation Tasks.", "stars": "434"}, {"name": "OpenCCG", "url": "https://github.com/OpenCCG/openccg", "description": "OpenCCG library for parsing and realization with CCG.", "stars": "201"}, {"name": "GrammaticalFramework", "url": "http://www.grammaticalframework.org/", "description": "A programming language for multilingual grammar applications."}, {"name": "EasyCCG", "url": "https://github.com/mikelewis0/easyccg", "description": "CCG: All combinators, common grammar format, parsing to logical form, parameter estimation for probabilistic CCG.", "stars": "58"}, {"name": "CCG Lab", "url": "https://github.com/bozsahin/ccglab", "description": "All combinators, common grammar format, parsing to logical form, parameter estimation for probabilistic CCG.", "stars": "26"}, {"name": "CCGweb", "url": "https://github.com/texttheater/ccgweb", "description": "A Web platform for parsing and annotation.", "stars": "6"}, {"name": "Cron Expression Descriptor", "url": "https://github.com/bradymholt/cron-expression-descriptor", "description": "A .NET library that converts cron expressions into human readable descriptions.", "stars": "898"}, {"name": "Number Words", "url": "https://github.com/tokenmill/numberwords", "description": "Convert a number to an approximated text expression: from '0.23' to 'less than a quarter'.", "stars": "194"}, {"name": "Writebot", "url": "https://docs.writebot.app", "description": "A NodeJS library that makes it easier to use GPT-3 by using presets."}, {"name": "Random Story Generator", "url": "https://github.com/aherriot/story-generator", "description": "Using Natural Language Generation (NLG) to create a random short story.", "stars": "62"}, {"name": "Tracery", "url": "https://github.com/galaxykate/tracery", "description": "A story-grammar generation library for JavaScript.", "stars": "2.1k"}, {"name": "aitextgen", "url": "https://github.com/minimaxir/aitextgen", "description": "A robust Python tool for text-based AI training and generation using GPT-2.", "stars": "1.8k"}, {"name": "graph-2-text", "url": "https://github.com/diegma/graph-2-text", "description": "Graph to sequence implemented in Pytorch combining Graph convolutional networks and opennmt-py.", "stars": "151"}, {"name": "Image Caption Generator", "url": "https://github.com/neural-nuts/image-caption-generator", "description": "A Neural Network based generative model for captioning images using Tensorflow.", "stars": "145"}, {"name": "lightnlg", "url": "https://github.com/kasnerz/lightnlg", "description": "A minimalistic codebase for finetuning and interacting with NLG models using PyTorch Lightning.", "stars": "3"}, {"name": "PaperRobot: Incremental Draft Generation of Scientific Ideas", "url": "https://github.com/EagleW/PaperRobot", "description": "We present a PaperRobot who performs as an automatic research assistant.", "stars": "468"}, {"name": "PPLM", "url": "https://github.com/uber-research/PPLM", "description": "Plug and Play Language Model implementation. Allows to steer topic and attributes of GPT-2 models.", "stars": "1.1k"}, {"name": "Question Generation using hugstransformers", "url": "https://github.com/patil-suraj/question_generation", "description": "Question generation is the task of automatically generating questions from a text paragraph.", "stars": "981"}, {"name": "Texar", "url": "https://github.com/asyml/texar", "description": "Texar is a toolkit aiming to support a broad set of machine learning, especially natural language processing and text generation tasks.", "stars": "2.4k"}, {"name": "textgenrnn", "url": "https://github.com/minimaxir/textgenrnn", "description": "Easily train your own text-generating neural network of any size and complexity on any text dataset with a few lines of code.", "stars": "4.9k"}, {"name": "This Word Does Not Exist", "url": "https://github.com/turtlesoupy/this-word-does-not-exist", "description": "This is a project allows people to train a variant of GPT-2 that makes up words, definitions and examples from scratch.", "stars": "1k"}, {"name": "Transformers", "url": "https://github.com/huggingface/transformers", "description": "State-of-the-art Natural Language Processing for TensorFlow 2.0 and PyTorch.", "stars": "111k"}, {"name": "Summary Generation From Structured Data", "url": "https://github.com/akanimax/natural-language-summary-generation-from-structured-data", "description": "For converting information present in the form of structured data into natural language text.", "stars": "183"}, {"name": "2022: Repairing the Cracked Foundation: A Survey of Obstacles in Evaluation Practices for Generated Text", "url": "https://arxiv.org/abs/2202.06935", "description": ""}, {"name": "2021: Vision: NLG Can Help Humanise Data and AI", "url": "https://ehudreiter.com/2021/03/17/vision-nlg-can-help-humanise-data-and-ai/", "description": ""}, {"name": "2020: The Curious Case of Neural Text Degeneration", "url": "https://openreview.net/forum?id=rygGQyrFvH", "description": ""}, {"name": "2020: A Gold Standard Methodology for Evaluating Accuracy in Data-To-Text Systems", "url": "https://arxiv.org/abs/2011.03992", "description": ""}, {"name": "2020: Evaluating the state-of-the-art of End-to-End Natural Language Generation: The E2E NLG challenge", "url": "https://www.sciencedirect.com/science/article/pii/S0885230819300919", "description": ""}, {"name": "2020: How to generate text: using different decoding methods for language generation with Transformers", "url": "https://huggingface.co/blog/how-to-generate", "description": ""}, {"name": "2020: Natural language generation: The commercial state ofthe art in 2020", "url": "https://www.cambridge.org/core/services/aop-cambridge-core/content/view/BA2417D73AF29F8073FF5B611CDEB97F/S135132492000025Xa.pdf/natural_language_generation_the_commercial_state_of_the_art_in_2020.pdf", "description": ""}, {"name": "2020: Turing-NLG: A 17-billion-parameter language model by Microsoft", "url": "https://www.microsoft.com/en-us/research/blog/turing-nlg-a-17-billion-parameter-language-model-by-microsoft/", "description": ""}, {"name": "2019: A Closer Look at Recent Results of Verb Selection for Data-to-Text NLG", "url": "https://www.inlg2019.com/assets/papers/178_Paper.pdf", "description": ""}, {"name": "2019: A Personalized Data-to-Text Support Tool for Cancer Patients", "url": "https://www.inlg2019.com/assets/papers/28_Paper.pdf", "description": ""}, {"name": "2019: Controlling Contents in Data-to-Document Generation with Human-Designed Topic Labels", "url": "https://www.inlg2019.com/assets/papers/79_Paper.pdf", "description": ""}, {"name": "2019: Generated Texts Must Be Accurate!", "url": "https://ehudreiter.com/2019/09/26/generated-texts-must-be-accurate/", "description": ""}, {"name": "2019: Hotel Scribe: Generating High Variation Hotel Descriptions", "url": "https://www.inlg2019.com/assets/papers/44_Paper.pdf", "description": ""}, {"name": "2019: Revisiting Challenges in Data-to-Text Generation with Fact Grounding", "url": "https://www.inlg2019.com/assets/papers/32_Paper.pdf", "description": ""}, {"name": "2017: Survey of the State of the Art in NaturalLanguage Generation: Core tasks, applicationsand evaluation", "url": "https://arxiv.org/pdf/1703.09902.pdf", "description": ""}, {"name": "2016: Natural Language Generation enhances human decision-making with uncertain information", "url": "https://arxiv.org/pdf/1606.03254.pdf", "description": ""}, {"name": "Accelerated Text", "url": "https://github.com/tokenmill/accelerated-text", "description": "Automatically generate multiple natural language descriptions of your data varying in wording and structure.", "stars": "734"}, {"name": "RosaeNLG", "url": "https://rosaenlg.org", "description": "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."}, {"name": "Twine", "url": "http://twinery.org/", "description": "An open-source tool for telling interactive, nonlinear stories."}, {"name": "Genl", "url": "https://github.com/kowey/GenI", "description": "Surface realiser (part of a Natural Language Generation system) using Tree Adjoining Grammar.", "stars": "22"}, {"name": "JSrealB", "url": "https://github.com/rali-udem/JSrealB", "description": "A JavaScript bilingual text realizer for web development.", "stars": "20"}, {"name": "SimpleNLG", "url": "https://github.com/simplenlg/simplenlg", "description": "Java API for Natural Language Generation.", "stars": "795"}, {"name": "SimpleNLG DE", "url": "https://github.com/sebischair/SimpleNLG-DE", "description": "German version of SimpleNLG 4.", "stars": "16"}, {"name": "SimpleNLG-EnFr", "url": "https://github.com/rali-udem/SimpleNLG-EnFr", "description": "SimpleNLG-EnFr 1.1 is a bilingual English/French adaption of SimpleNLG v4.2.", "stars": "25"}, {"name": "calyx", "url": "https://github.com/maetl/calyx", "description": "A Ruby library for generating text with recursive template grammars.", "stars": "60"}, {"name": "nalgene", "url": "https://github.com/spro/nalgene", "description": "Natural language generation language.", "stars": "54"}, {"name": "StringTemplate", "url": "https://www.stringtemplate.org/", "description": "Java template engine (with ports for C##, Objective-C, JavaScript, Scala) for generating source code, web pages, emails, or any other formatted text output."}, {"name": "Data-To-Text: Generating Textual Summaries of Complex Data - Ehud Reiter", "url": "https://www.youtube.com/watch?v=kFRw-wk5YOA", "description": ""}, {"name": "Imitation Learning and its Application to Natural Language Generation", "url": "https://slideslive.com/38922816/imitation-learning-and-its-application-to-natural-language-generation", "description": ""}, {"name": "Natural Language Generation (Introduction)", "url": "https://www.youtube.com/watch?v=4fjM72lbJaw", "description": ""}, {"name": "Strata Data Conference | The future of natural language generation: 2017-2027", "url": "https://www.youtube.com/watch?v=Ls7elVbN8bI", "description": ""}, {"name": "The Quest for Automated Story Generation - Mark Riedl", "url": "https://www.youtube.com/watch?v=wgcDUX_BPpk", "description": ""}]}], "name": ""} |