Commonsense understanding is a long-term goal of natural language processing yet to be resolved. One standard testbed for commonsense understanding is Story Cloze Test (SCT) [22], In SCT,
given a 4-sentences story, we are expected to select the proper
ending out of two proposed candidates. The training set in SCT
only contains unlabeled stories, previous works usually adopt the
small labeled development data for training, which ignored the suffcient training data and, essentially, not reveal the commonsense
reasoning procedure. In this paper, we propose an unsupervised
sequence-to-sequence method for story reading comprehension,
we only adopt the unlabeled story and directly model the contexttarget inference probability. We propose a loss-reweight training
strategy for the seq-to-seq model to dynamically tuning the training process. Experimental results demonstrate the advantage of
the proposed model and it achieves the comparable results with
supervised methods on SCT.