SOTAVerified

MITRE at SemEval-2018 Task 11: Commonsense Reasoning without Commonsense Knowledge

2018-06-01SEMEVAL 2018Unverified0· sign in to hype

Elizabeth Merkhofer, John Henderson, David Bloom, Laura Strickhart, Guido Zarrella

Unverified — Be the first to reproduce this paper.

Reproduce

Abstract

This paper describes MITRE's participation in SemEval-2018 Task 11: Machine Comprehension using Commonsense Knowledge. The techniques explored range from simple bag-of-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.

Tasks

Reproductions