Displaying 1 to 20 from 24 results

textgenrnn - Easily train your own text-generating neural network of any size and complexity on any text dataset with a few lines of code

  •    Python

Easily train your own text-generating neural network of any size and complexity on any text dataset with a few lines of code, or quickly train on a text using a pretrained model. The included model can easily be trained on new texts, and can generate appropriate text even after a single pass of the input data.

delta - DELTA is a deep learning based natural language and speech processing platform.

  •    Python

DELTA is a deep learning based end-to-end natural language and speech processing platform. DELTA aims to provide easy and fast experiences for using, deploying, and developing natural language processing and speech models for both academia and industry use cases. DELTA is mainly implemented using TensorFlow and Python 3. For details of DELTA, please refer to this paper.

gpt-2-simple - Python package to easily retrain OpenAI's GPT-2 text-generating model on new texts

  •    Python

A simple Python package that wraps existing model fine-tuning and generation scripts for OpenAI's GPT-2 text generation model (specifically the "small" 124M and "medium" 355M hyperparameter versions). Additionally, this package allows easier generation of text, generating to a file for easy curation, allowing for prefixes to force the text to start with a given phrase. You can use gpt-2-simple to retrain a model using a GPU for free in this Colaboratory notebook, which also demos additional features of the package.

PaperRobot - Code for PaperRobot: Incremental Draft Generation of Scientific Ideas

  •    Python

You can click the following links for detailed installation instructions. PubMed Paper Reading Dataset This dataset gathers 14,857 entities, 133 relations, and entities corresponding tokenized text from PubMed. It contains 875,698 training pairs, 109,462 development pairs, and 109,462 test pairs.

gpt-2-cloud-run - Text-generation API via GPT-2 for Cloud Run

  •    HTML

App for building a text-generation API for generating text from OpenAI's GPT-2 via gpt-2-simple, and running it in a scalable manner and effectively free via Google's Cloud Run. This app is intended to be used to easily and cost-effectively allow others to play with a finetuned GPT-2 model on another dataset, and allow programmatic access to the generated text. The base app.py runs starlette for async/futureproofness, and is easily hackable if you want to modify GPT-2's input/output, force certain generation parameters, or want to add additional features/endpoints such as tweeting the generated result.

DeepTingle - A Deep NN used to generate stories which will tingle your butt.

  •    HTML

A Deep NN used to generate stories which will tingle your butt. To test the system visit http://www.deeptingle.net. The core file is DeepTingle Words.ipynb. This code is used to train the current neural network used in the website. It contains all the different experiments used in the published paper.

keras-text-generation - RNN text generation using Keras for word and character level models.

  •    Python

Recurrent neural network (RNN) text generation using Keras. Generating text with neural networks is fun, and there are a ton of projects and standalone scripts to do it. This project does not provide any groundbreaking features over what it already out there, but attempts to be a good, well documented place to start playing with text generation within the Keras framework. It handles the nitty-gritty details of loading a text corpus and feeding it into a Keras model.

LSTM-Text-Generation - Tons of fun with text and recurrent neural networks! Let your computer read a book and tell you its own story

  •    Hy

During the time that I was writing my bachelor's thesis Sequence-to-Sequence Learning of Financial Time Series in Algorithmic Trading (in which I used LSTM-based RNNs for modeling the thesis problem), I became interested in natural language processing. After reading Andrej Karpathy's blog post titled The Unreasonable Effectiveness of Recurrent Neural Networks, I decided to give text generation using LSTMs for NLP a go. Although slightly trivial, the project still comprises an interesting program and demo, and gives really interesting (and sometimes very funny) results. I implemented the program over the course of a weekend in Hy (a LISP built on top of Python) using Keras and TensorFlow. You can train the model on any text sources you like. Remember to give it enough time to go over at least fifty epochs, otherwise the generated text will not be very interesting, rather seemingly random garbage.

presswork - Text generation workbench, starting with Markov Chains

  •    Python

So far, it's all about Markov Chains. Here's a great visual explanation of Markov Chains. Given a bunch of text, model it, and generate "probable" new sentences. I'd like to add other tools to the toolkit, building off of this foundation.

php-text-generator - Fast SEO text generator on a mask.

  •    PHP

Fast SEO text generator on a mask. Written in PHP. I do not use regular expressions and the fastest. I covered tests and simple! Supporting recursive text generation rules. It supports multiple encodings.

markov - A generic markov chain implementation in Rust.

  •    Rust

A generic implementation of a Markov chain in Rust. It supports all types that implement Eq, Hash, and Clone, and has some specific helpers for working with String as text generation is the most likely use case. You can find up-to-date, ready-to-use documentation online on docs.rs. Note: markov is in passive maintenance mode. It should work well for its intended use case (largely textual generation, especially in chat bots and the like), but will likely not grow to any further use cases. If it does not meet your needs in a broad sense, you should likely fork it or develop a more purpose-built library. Nevertheless, bug reports will still be triaged and fixed.

ctrl-sum - Resources for the "CTRLsum: Towards Generic Controllable Text Summarization" paper

  •    Python

This repo includes instructions for using pretrained CTRLsum models as well as training new models. CTRLsum is a generic controllable summarization system to manipulate text summaries given control tokens in the form of keywords or prefix. CTRLsum is also able to achieve strong (e.g. state-of-the-art on CNN/Dailymail) summarization performance in an uncontrolled setting.

Describing_a_Knowledge_Base - Code for Describing a Knowledge Base

  •    Python

Put the Wikipedia Person and Animal Dataset under the Describing a Knowledge Base folder. Unzip it. Randomly split the data into train, dev and test by runing split.py under utils folder.

ReviewRobot - Code for ReviewRobot: Explainable Paper Review Generation based on Knowledge Synthesis

  •    Python

You can click the following links for detailed installation instructions. ReviewRobot dataset This dataset contains 8,110 paper and review pairs and background KG from 174,165 papers. It also contains information extraction results from SciIE, various knowledge graphs built on the IE results, and human annotation for paper-review pairs. The detailed information can be found here.

Writing-editing-Network - Code for Paper Abstract Writing through Editing Mechanism

  •    Python

Put the acl_titles_and_abstracts.txt under the Writing-editing network folder. Randomly split the data into train, dev and test by runing split_data.py. Hyperparameter can be adjust in the Config class of main.py.

text-generator - Golang text generator

  •    Go

Fast text generator on a mask. Written in Golang. I do not use regular expressions and the fastest. I covered tests and simple! Supporting recursive text generation rules.

gap-text2sql - GAP-text2SQL: Learning Contextual Representations for Semantic Parsing with Generation-Augmented Pre-Training

  •    Python

[2020/02/05] Support to run the model on own databases and queries. Check out the notebook. Most recently, there has been significant interest in learning contextual representations for various NLP tasks, by leveraging large scale text corpora to train large neural language models with self-supervised learning objectives, such as Masked Language Model (MLM). However, based on a pilot study, we observe three issues of existing general-purpose language models when they are applied to text-to-SQL semantic parsers: fail to detect column mentions in the utterances, fail to infer column mentions from cell values, and fail to compose complex SQL queries. To mitigate these issues, we present a model pre-training framework, Generation-Augmented Pre-training (GAP), that jointly learns representations of natural language utterances and table schemas by leveraging generation models to generate pre-train data. GAP MODEL is trained on 2M utterance-schema pairs and 30K utterance-schema-SQL triples, whose utterances are produced by generative models. Based on experimental results, neural semantic parsers that leverage GAP MODEL as a representation encoder obtain new state-of-the-art results on both SPIDER and CRITERIA-TO-SQL benchmarks.

We have large collection of open source products. Follow the tags from Tag Cloud >>

Open source products are scattered around the web. Please provide information about the open source projects you own / you use. Add Projects.