Texygen: A Benchmarking Platform for Text Generation Models

Abstract

We introduce Texygen, a benchmarking platform to support research on open-domain text generation models. Texygen has not only implemented a majority of text generation models, but also covered a set of metrics that evaluate the diversity, the quality and the consistency of the generated texts. The Texygen platform could help standardize the research on text generation and facilitate the sharing of fine-tuned open-source implementations among researchers for their work. As a consequence, this would help in improving the reproductivity and reliability of future research work in text generation.

arXiv comment4 pages

References in corpus (7)

• Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
• Adversarial Learning for Neural Dialogue Generation
• GANS for Sequences of Discrete Elements with the Gumbel-softmax Distribution
• How (not) to Train your Generative Model: Scheduled Sampling, Likelihood, Adversary?
• Maximum-Likelihood Augmented Discrete Generative Adversarial Networks
• Long Text Generation via Adversarial Training with Leaked Information
• Adversarial Feature Matching for Text Generation

Cited by in corpus (28)

• Evaluation of Text Generation: A Survey
• Language GANs Falling Short
• Topic-Guided Variational Autoencoders for Text Generation
• Neural Text Generation: Past, Present and Beyond
• Defense Methods Against Adversarial Examples for Recurrent Neural Networks
• CoT: Cooperative Training for Generative Modeling of Discrete Data
• Understanding Multi-Turn Toxic Behaviors in Open-Domain Chatbots
• EmoUS: Simulating User Emotions in Task-Oriented Dialogues
• Towards Generating Long and Coherent Text with Multi-Level Latent Variable Models
• Move Forward and Tell: A Progressive Generator of Video Descriptions
• ColdGANs: Taming Language GANs with Cautious Sampling Strategies
• CatGAN: Category-aware Generative Adversarial Networks with Hierarchical Evolutionary Learning for Category Text Generation
• mu-Forcing: Training Variational Recurrent Autoencoders for Text Generation
• Extractive Summary as Discrete Latent Variables
• Variational Prefix Tuning for Diverse and Accurate Code Summarization Using Pre-trained Language Models
• Unsupervised Text Embedding Space Generation Using Generative Adversarial Networks for Text Synthesis
• Controllable and Diverse Text Generation in E-commerce
• Meta-CoTGAN: A Meta Cooperative Training Paradigm for Improving Adversarial Text Generation
• Adversarial Sub-sequence for Text Generation
• Mathematical Word Problem Generation from Commonsense Knowledge Graph and Equations
• Towards Controllable and Personalized Review Generation
• Learning from Multiple Sources for Data-to-Text and Text-to-Data
• SDA: Improving Text Generation with Self Data Augmentation
• Middle-Out Decoding
• Linguacodus: A Synergistic Framework for Transformative Code Generation in Machine Learning Pipelines
• Approximate Random Dropout
• Evaluating Computational Language Models with Scaling Properties of Natural Language
• Generation of Synthetic Electronic Medical Record Text