Graph-based Neural Sentence Ordering
arXiv:1912.07225
Abstract
Sentence ordering is to restore the original paragraph from a set of sentences. It involves capturing global dependencies among sentences regardless of their input order. In this paper, we propose a novel and flexible graph-based neural sentence ordering model, which adopts graph recurrent network \cite{Zhang:acl18} to accurately learn semantic representations of the sentences. Instead of assuming connections between all pairs of input sentences, we use entities that are shared among multiple sentences to make more expressive graph representations with less noise. Experimental results show that our proposed model outperforms the existing state-of-the-art systems on several benchmark datasets, demonstrating the effectiveness of our model. We also conduct a thorough analysis on how entities help the performance.
IJCAI2019
References in corpus (7)
- ADADELTA: An Adaptive Learning Rate Method
- Inferring Strategies for Sentence Ordering in Multidocument News Summarization
- Graph2Seq: Graph to Sequence Learning with Attention-based Neural Networks
- Sentence Ordering and Coherence Modeling using Recurrent Neural Networks
- Sentence-State LSTM for Text Representation
- A Graph-to-Sequence Model for AMR-to-Text Generation
- N-ary Relation Extraction using Graph State LSTM