Mxgra at SemEval-2020 Task 4: Common Sense Making with Next Token Prediction

Abstract

In this paper, we explore solutions to a common sense making task in which a model must discern which of two sentences is against common sense. We used a pre-trained language model which we used to calculate complexity scores for input to discern which sentence contained an unlikely sequence of tokens. Other approaches we tested were word vector distances, which were used to find semantic outliers within a sentence, and siamese network. By using the pre-trained language model to calculate perplexity scores based on the sequence of tokens in input sentences, we achieved an accuracy of 75 percent.

Tasks

Reproductions