NAREOR: The Narrative Reordering Problem
Varun Gangal, Steven Y. Feng, Malihe Alikhani, Teruko Mitamura, Eduard, Hovy

TL;DR
This paper introduces the Narrative Reordering task, exploring how changing story order affects interpretation, and presents a dataset, methods, and evaluations demonstrating its challenges and potential applications.
Contribution
It proposes the NAREOR task, creates the NAREORC dataset with human rewritings, and develops models and evaluation metrics for narrative reordering.
Findings
Models perform decently but NAREOR remains challenging.
NAREOR enables interesting story variations and adversarial testing.
Potential applications include education and clinical narrative analysis.
Abstract
Many implicit inferences exist in text depending on how it is structured that can critically impact the text's interpretation and meaning. One such structural aspect present in text with chronology is the order of its presentation. For narratives or stories, this is known as the narrative order. Reordering a narrative can impact the temporal, causal, event-based, and other inferences readers draw from it, which in turn can have strong effects both on its interpretation and interestingness. In this paper, we propose and investigate the task of Narrative Reordering (NAREOR) which involves rewriting a given story in a different narrative order while preserving its plot. We present a dataset, NAREORC, with human rewritings of stories within ROCStories in non-linear orders, and conduct a detailed analysis of it. Further, we propose novel task-specific training methods with suitable…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
Taxonomy
TopicsTopic Modeling · Natural Language Processing Techniques · Computational and Text Analysis Methods
MethodsGated Linear Unit · Multi-Head Attention · Attention Is All You Need · Linear Layer · Absolute Position Encodings · Position-Wise Feed-Forward Layer · Adafactor · Inverse Square Root Schedule · BART · SentencePiece
