STaCK: Sentence Ordering with Temporal Commonsense Knowledge
This work addresses the problem of document coherence for natural language processing applications, but it is incremental as it builds on existing methods with a novel integration of temporal knowledge.
The paper tackles the sentence order prediction task by introducing STaCK, a framework that uses graph neural networks and temporal commonsense knowledge to model global information, reporting results on five datasets and showing it is naturally suitable for order prediction.
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.