MITRE at SemEval-2018 Task 11: Commonsense Reasoning without Commonsense Knowledge
Elizabeth Merkhofer, John C. Henderson, David Bloom, Laura Strickhart, Guido Zarrella · 2018
This paper describes MITRE's participation in SemEval-2018 Task 11: Machine Comprehension using Commonsense Knowledge.The techniques explored range from simple bagof-ngrams classifiers to neural architectures with varied attention and alignment mechanisms.Logistic regression ties the systems together into an ensemble submitted for evaluation.The resulting system answers reading comprehension questions with 82.27% accuracy.