End-to-End Neural Sentence Ordering Using Pointer Network
This addresses sentence ordering for NLP applications, but it is incremental as it builds on existing pointer network methods.
The paper tackles the sentence ordering problem in NLP by proposing an end-to-end neural approach using a pointer network to reduce error propagation and incorporate contextual information, showing effectiveness in experiments.
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.