0
GLTR: Statistical Detection and Visualization of Generated Text
Sebastian Gehrmann, Hendrik Strobelt, Alexander M. Rush, 2019. arXiv.
GLTR, a tool that shows how predictable each word of a text is to a language model, to help people spot machine-generated text.
What it's used for here
The procedure-fingerprinting survey lists it among ways of detecting text produced by a procedure.
Cited by on this site 1 record
1 methods surveys
SRCEncoding procedures
Cite it
Gehrmann, S., Strobelt, H., & Rush, A. M. (2019). GLTR: Statistical Detection and Visualization of Generated Text. arXiv. https://arxiv.org/abs/1906.04043
@article{gehrmann2019gltr,
author = {Gehrmann, Sebastian and Strobelt, Hendrik and Rush, Alexander M.},
title = {GLTR: Statistical Detection and Visualization of Generated Text},
journal = {arXiv},
year = {2019},
url = {https://arxiv.org/abs/1906.04043}
}TY - GEN TI - GLTR: Statistical Detection and Visualization of Generated Text AU - Gehrmann, Sebastian AU - Strobelt, Hendrik AU - Rush, Alexander M. PY - 2019 JO - arXiv UR - https://arxiv.org/abs/1906.04043 ER -
Gehrmann, Sebastian et al.. “GLTR: Statistical Detection and Visualization of Generated Text.” arXiv (2019).