A Strong Lexical Matching Method for the Machine Comprehension Test

Machine comprehension of text is theoverarching goal of a great deal of re-search in natural language processing. TheMachine Comprehension Test (Richard-son et al., 2013) was recently proposed toassess methods on an open-domain, exten-sible, and easy-to-evaluate task consistingof two datasets. In this paper we developa lexical matching method that takes intoaccount multiple context windows, ques-tion types and coreference resolution. Weshow that the proposed method outper-forms the baseline of Richardson et al.(2013), and despite its relative simplicity,is comparable to recent work using ma-chine learning. We hope that our approachwill inform future work on this task. Fur-thermore, we argue that MC500 is harderthan MC160 due to the way question an-swer pairs were created.