Improving Graph-based Sentence Ordering with Iteratively Predicted Pairwise Orderings
This work addresses sentence ordering for natural language processing tasks, offering an incremental improvement by integrating complementary model types.
The paper tackles the problem of sentence ordering by combining pairwise and set-to-sequence models, proposing a novel framework that uses iterative graph-based classifiers to predict pairwise orderings and achieves state-of-the-art performance with BERT and FHDecoder on five datasets.
Dominant sentence ordering models can be classified into pairwise ordering models and set-to-sequence models. However, there is little attempt to combine these two types of models, which inituitively possess complementary advantages. In this paper, we propose a novel sentence ordering framework which introduces two classifiers to make better use of pairwise orderings for graph-based sentence ordering. Specially, given an initial sentence-entity graph, we first introduce a graph-based classifier to predict pairwise orderings between linked sentences. Then, in an iterative manner, based on the graph updated by previously predicted high-confident pairwise orderings, another classifier is used to predict the remaining uncertain pairwise orderings. At last, we adapt a GRN-based sentence ordering model on the basis of final graph. Experiments on five commonly-used datasets demonstrate the effectiveness and generality of our model. Particularly, when equipped with BERT and FHDecoder, our model achieves state-of-the-art performance.