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 improve the reproductivity and reliability of future research work in text generation.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
High values of k are needed to make top-k sampling match human statistics.
“Vocabulary usage and Self-BLEU (Zhu et al., 2018) statistics reveal that high values of k are needed to make top-k sampling match human statistics.”
From The Curious Case of Neural Text Degeneration (2019) · cites this paper as Zhu et al., 2018
The citation lists haven’t been fetched yet
References 10 · Cited by 408
- Authors
- Zhu, Y., Lu, S., Zheng, L., Guo, J., Zhang, W., Wang, J., & Yu, Y.
- Affiliations
- Shanghai Jiao Tong University (CN)
- University College London, London, United Kingdom
- Venue
- The 41st International ACM SIGIR Conference on Research & Development in Information Retrieval
- Publisher
- ACM
- Published
- 2018-06-27
- Pages
- 1097-1100
- OpenAlex
- W2963456134
- Cited by
- 408
- References
- 10
- Citations by year
- 2026: 41 · 2025: 44 · 2024: 34 · 2023: 56 · 2022: 46 · 2021: 78 · 2020: 64 · 2019: 39 · 2018: 6
- FWCI
- 19.08
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) (publishedVersion)
- Funders
- DIDI Collaborative Research Funds
- Shanghai Sailing Program (17YF1428200)
- National Natural Science Foundation of China (61702327)
- MSRA Collaborative Research
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Physical Sciences › Computer Science › Artificial Intelligence › Natural Language Processing Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Multimodal Machine Learning Applications
- Keywords
- benchmarking platform, text generation models, evaluation metrics, text diversity, text quality, reproducibility, research standardization
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
