A Simple Machine Learning Method for Commonsense Reasoning? A Short Commentary on Trinh & Le (2018)
Artificial Intelligence
2018-10-02 v1 Computation and Language
Machine Learning
Abstract
This is a short Commentary on Trinh & Le (2018) ("A Simple Method for Commonsense Reasoning") that outlines three serious flaws in the cited paper and discusses why data-driven approaches cannot be considered as serious models for the commonsense reasoning needed in natural language understanding in general, and in reference resolution, in particular.
Cite
@article{arxiv.1810.00521,
title = {A Simple Machine Learning Method for Commonsense Reasoning? A Short Commentary on Trinh & Le (2018)},
author = {Walid S. Saba},
journal= {arXiv preprint arXiv:1810.00521},
year = {2018}
}
Comments
5 pages