Main content
MLRegTest
Date created: | Last Updated:
: DOI | ARK
Creating DOI. Please wait...
Category: Project
Description: UPDATE (November 8, 2023): This archive has been superseded by MLRegTest on Dryad. Please use the Dryad to access MLRegTest. See the WIKI or README for more information and link to Dryad. ===== MLRegTest is a benchmark for machine learning systems on sequence classification, which contains training, development, and test sets from 1,800 regular languages. MLRegTest organizes its languages according to their logical complexity (monadic second order, first order, propositional, or monomial expressions) and the kind of logical literals (string, tier-string, subsequence, or combinations thereof). The logical complexity and choice of literal provides a systematic way to understand different kinds of long-distance dependencies in regular languages, and therefore to understand the capacities of different ML systems to learn such long-distance dependencies. Details are described in the arxiv preprint "MLRegTest: A Benchmark for the Machine Learning of Regular Languages".
UPDATE (November 8, 2023)
In spring 2023, unintended biases were discovered in the MLRegTest training, dev, and test sets. The sources of error causing these biases have been corrected, and the models have been retrained, and evaluated. The updated paper is being posted to arxiv as version 2. The new datasets and models are available at DRYAD here: https://doi.org/10.5061/dryad.dncjsxm4h
Related S…
Files
Files can now be accessed and managed under the Files tab.
Citation
Recent Activity
Unable to retrieve logs at this time. Please refresh the page or contact support@osf.io if the problem persists.
Start managing your projects on the OSF today.
Free and easy to use, the Open Science Framework supports the entire research lifecycle: planning, execution, reporting, archiving, and discovery.