STaCK: Sentence Ordering with Temporal Commonsense Knowledge

TL;DR

This paper presents STaCK, a graph neural network framework that leverages temporal commonsense knowledge to accurately predict the correct order of sentences in a document, improving understanding of coherence and chronology.

Contribution

STaCK introduces a novel graph neural network approach that incorporates temporal commonsense knowledge for sentence order prediction, addressing limitations of previous methods.

Findings

Outperforms existing methods on five datasets

Effectively models global temporal information

Demonstrates the importance of commonsense knowledge in ordering

Abstract

Sentence order prediction is the task of finding the correct order of sentences in a randomly ordered document. Correctly ordering the sentences requires an understanding of coherence with respect to the chronological sequence of events described in the text. Document-level contextual understanding and commonsense knowledge centered around these events are often essential in uncovering this coherence and predicting the exact chronological order. In this paper, we introduce STaCK -- a framework based on graph neural networks and temporal commonsense knowledge to model global information and predict the relative order of sentences. Our graph network accumulates temporal evidence using knowledge of `past' and `future' and formulates sentence ordering as a constrained edge classification problem. We report results on five different datasets, and empirically show that the proposed method is naturally suitable for order prediction. The implementation of this work is publicly available at: https://github.com/declare-lab/sentence-ordering.