End-to-End Neural Sentence Ordering Using Pointer Network

TL;DR

This paper introduces an end-to-end neural model using pointer networks for sentence ordering in NLP, effectively capturing contextual information and reducing error propagation compared to previous pair-wise methods.

Contribution

It presents a novel end-to-end approach with pointer networks that improves sentence ordering by leveraging full contextual information and minimizing error propagation.

Findings

The proposed model outperforms previous pair-wise methods.

Experimental results demonstrate the effectiveness of the approach.

Source code and dataset are publicly available.

Abstract

Sentence ordering is one of important tasks in NLP. Previous works mainly focused on improving its performance by using pair-wise strategy. However, it is nontrivial for pair-wise models to incorporate the contextual sentence information. In addition, error prorogation could be introduced by using the pipeline strategy in pair-wise models. In this paper, we propose an end-to-end neural approach to address the sentence ordering problem, which uses the pointer network (Ptr-Net) to alleviate the error propagation problem and utilize the whole contextual information. Experimental results show the effectiveness of the proposed model. Source codes and dataset of this paper are available.