STaCK: Sentence Ordering with Temporal Commonsense Knowledge

by   Deepanway Ghosal, et al.
University of Michigan
Singapore University of Technology and Design

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:


page 1

page 2

page 3

page 4


Topological Sort for Sentence Ordering

Sentence ordering is the task of arranging the sentences of a given text...

Neural Sentence Ordering Based on Constraint Graphs

Sentence ordering aims at arranging a list of sentences in the correct o...

InsertGNN: Can Graph Neural Networks Outperform Humans in TOEFL Sentence Insertion Problem?

Sentence insertion is a delicate but fundamental NLP problem. Current ap...

Does Commonsense help in detecting Sarcasm?

Sarcasm detection is important for several NLP tasks such as sentiment i...

A New Sentence Ordering Method Using BERT Pretrained Model

Building systems with capability of natural language understanding (NLU)...

Evaluating Text Coherence at Sentence and Paragraph Levels

In this paper, to evaluate text coherence, we propose the paragraph orde...

Logic and Commonsense-Guided Temporal Knowledge Graph Completion

A temporal knowledge graph (TKG) stores the events derived from the data...

Please sign up or login with your details

Forgot password? Click here to reset