Texygen: A Benchmarking Platform for Text Generation Models

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 improve the reproductivity and reliability of future research work in text generation.

cs.CL cs.IR cs.LG Computer Science

Paper

References (17)

01Long Text Generation via Adversarial Training with Leaked InformationJiaxian Guo, Sidi Lu, Han Cai et al.2017 · AAAI Conference on Artificial Intelligence · 533 citations In Library

02Adversarial Feature Matching for Text GenerationYizhe Zhang, Zhe Gan, Kai Fan et al.2017 · International Conference on Machine Learning · 364 citations In Library

03Adversarial Ranking for Language GenerationKevin Lin, Dianqi Li, Xiaodong He et al.2017 · Neural Information Processing Systems · 351 citations In Library

04IRGAN: A Minimax Game for Unifying Generative and Discriminative Information Retrieval ModelsJun Wang, Lantao Yu, Weinan Zhang et al.2017 · Annual International ACM SIGIR Conference on Research and Development in Information Retrieval · 686 citations In Library

05Maximum-Likelihood Augmented Discrete Generative Adversarial NetworksTong Che, Yanran Li, Ruixiang Zhang et al.2017 · arXiv.org · 250 citations In Library

06Adversarial Learning for Neural Dialogue GenerationJiwei Li, Will Monroe, Tianlin Shi et al.2017 · Conference on Empirical Methods in Natural Language Processing · 918 citations In Library

07GANS for Sequences of Discrete Elements with the Gumbel-softmax DistributionMatt J. Kusner, José Miguel Hernández-Lobato2016 · arXiv.org · 341 citations In Library

08SeqGAN: Sequence Generative Adversarial Nets with Policy GradientLantao Yu, Weinan Zhang, Jun Wang et al.2016 · AAAI Conference on Artificial Intelligence · 2.6k citations In Library

09TensorFlow: A system for large-scale machine learningMartín Abadi, P. Barham, Jianmin Chen et al.2016 · USENIX Symposium on Operating Systems Design and Implementation · 20k citations In Library

10How (not) to Train your Generative Model: Scheduled Sampling, Likelihood, Adversary?Ferenc Huszár2015 · arXiv.org · 317 citations In Library

11Show, Attend and Tell: Neural Image Caption Generation with Visual AttentionKe Xu, Jimmy Ba, Ryan Kiros et al.2015 · International Conference on Machine Learning · 11k citations In Library

12Neural Machine Translation by Jointly Learning to Align and TranslateDzmitry Bahdanau, Kyunghyun Cho, Yoshua Bengio2014 · International Conference on Learning Representations · 30k citations In Library

Scroll for more · 5 remaining

Similar papers

Texar: A Modularized, Versatile, and Extensible Toolkit for Text GenerationZhiting Hu, Haoran Shi, Bowen Tan et al.2018 · Annual Meeting of the Association for Computational Linguistics · 56 citations In Library

CoTK: An Open-Source Toolkit for Fast Development and Fair Evaluation of Text GenerationFei Huang, Dazhen Wan, Shao, Zhihong et al.2020 · arXiv (Cornell University) In Library

MTG: A Benchmark Suite for Multilingual Text GenerationYiran Chen, Zhenqiao Song, Xianze Wu et al.2021 · arXiv (Cornell University) In Library

TextBox: A Unified, Modularized, and Extensible Framework for Text GenerationJunyi Li, Tianyi Tang, Gaole He et al.2021 · arXiv (Cornell University) · 30 citations In Library

WeGenBench: A Multidimensional Diagnostic Benchmark towards Text-to-Image Model OptimizationQian Liang, Xiaomin Li, Ying Zhang et al.2026 · 0 citations In Library

TURINGBENCH: A Benchmark Environment for Turing Test in the Age of Neural Text GenerationAdaku Uchendu, Zeyu Ma, Thai Le et al.2021 In Library

MTG: A Benchmark Suite for Multilingual Text GenerationYiran Chen, Zhenqiao Song, Xianze Wu et al.2022 · Findings of the Association for Computational Linguistics: NAACL 2022 In Library

TURINGBENCH: A Benchmark Environment for Turing Test in the Age of Neural Text GenerationAdaku Uchendu, Zeyu Ma, Thái Hoàng Lê et al.2021 · arXiv (Cornell University) · 192 citations In Library

Modern Methods for Text GenerationDimas Muñoz-Montesinos2020 · arXiv (Cornell University) In Library

Structured Human Assessment of Text-to-Image Generative ModelsC. Corneanu, Qianli Feng, Aleix M. Martínez2025 · IEEE Workshop/Winter Conference on Applications of Computer Vision · 1 citation In Library

Source of record

arXiv

44B

Welcome.

This panel sticks with you. Pick anything below and it opens right beside it, so you can dig through 60,000-plus records without ever losing your spot here.

Travel 44B

LibraryPapers, policy, standards, statute LabsEvery organization building AI ModelsIntelligence, price, and speed BenchmarksThe evaluation catalog IncidentsAI failures and harms SearchOne field across everything DashboardThe state of AI accountability in NY 44B RegistryThe Art. 44-B compliance portal