Litcius/Paper detail

BERT-enhanced Relational Sentence Ordering Network

Baiyun Cui, Yingming Li, Zhongfei Zhang

202032 citationsDOIOpen Access PDF

Abstract

In this paper, we introduce a novel BERTenhanced Relational Sentence Ordering Network (referred to as BERSON) by leveraging BERT for capturing a better dependency relationship among sentences to enhance the coherence modeling for the entire paragraph. In particular, we develop a new Relational Pointer Decoder (referred as RPD) by incorporating the relative ordering information into the pointer network with a Deep Relational Module (referred as DRM), which utilizes BERT to exploit the deep semantic connection and relative ordering between sentences. This enables us to strengthen both local and global dependencies among sentences. Extensive evaluations are conducted on six public datasets. The experimental results demonstrate the effectiveness and promise of BERSON, showing a significant improvement over the state-of-the-art by a wide margin.

Topics & Concepts

Pointer (user interface)Computer scienceParagraphSentenceExploitMargin (machine learning)Dependency (UML)Coherence (philosophical gambling strategy)Artificial intelligenceNatural language processingMachine learningWorld Wide WebComputer securityQuantum mechanicsPhysicsTopic ModelingNatural Language Processing TechniquesAdvanced Graph Neural Networks
BERT-enhanced Relational Sentence Ordering Network | Litcius