Topological Sort for Sentence Ordering

05/01/2020
by   Shrimai Prabhumoye, et al.
0

Sentence ordering is the task of arranging the sentences of a given text in the correct order. Recent work using deep neural networks for this task has framed it as a sequence prediction problem. In this paper, we propose a new framing of this task as a constraint solving problem and introduce a new technique to solve it. Additionally, we propose a human evaluation for this task. The results on both automatic and human metrics across four different datasets show that this new technique is better at capturing coherence in documents.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
09/06/2021

STaCK: Sentence Ordering with Temporal Commonsense Knowledge

Sentence order prediction is the task of finding the correct order of se...
research
03/25/2021

BERT4SO: Neural Sentence Ordering by Fine-tuning BERT

Sentence ordering aims to arrange the sentences of a given text in the c...
research
06/05/2020

Evaluating Text Coherence at Sentence and Paragraph Levels

In this paper, to evaluate text coherence, we propose the paragraph orde...
research
11/08/2016

Sentence Ordering and Coherence Modeling using Recurrent Neural Networks

Modeling the structure of coherent texts is a key NLP problem. The task ...
research
03/28/2021

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

Sentence insertion is a delicate but fundamental NLP problem. Current ap...
research
08/26/2021

A New Sentence Ordering Method Using BERT Pretrained Model

Building systems with capability of natural language understanding (NLU)...
research
10/13/2021

Improving Graph-based Sentence Ordering with Iteratively Predicted Pairwise Orderings

Dominant sentence ordering models can be classified into pairwise orderi...

Please sign up or login with your details

Forgot password? Click here to reset