Recognizing Arrow Of Time In The Short Stories
This addresses a challenging task in natural language processing for understanding temporal order in narratives, but it is incremental as it applies existing methods to new data.
The paper tackled the problem of recognizing the arrow of time in short stories by collecting a novel dataset and showing that a pre-trained BERT architecture achieves reasonable accuracy, outperforming RNN-based methods.
Recognizing arrow of time in short stories is a challenging task. i.e., given only two paragraphs, determining which comes first and which comes next is a difficult task even for humans. In this paper, we have collected and curated a novel dataset for tackling this challenging task. We have shown that a pre-trained BERT architecture achieves reasonable accuracy on the task, and outperforms RNN-based architectures.