Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Texygen: A Benchmarking Platform for Text Generation Models

About

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.

Yaoming Zhu, Sidi Lu, Lei Zheng, Jiaxian Guo, Weinan Zhang, Jun Wang, Yong Yu• 2018

Related benchmarks

TaskDatasetResultRank
Simile Creativity EvaluationSimile candidates
Pearson R0.196
9
Text GenerationWebText--
9
Simile Recommendation RankingSimile Recommendation Dataset
HR@125.7
8
Open-ended text generation evaluation (Human-like)Web text--
2
Open-ended text generation evaluation (Discriminator Accuracy)News--
1
Open-ended text generation evaluation (Discriminator Accuracy)Stories--
1
Showing 6 of 6 rows

Other info

Follow for update