An entity-driven recursive neural network model for chinese discourse coherence modeling

TL;DR

This paper introduces an entity-driven recursive neural network model tailored for Chinese discourse coherence evaluation, effectively capturing entity overlaps and outperforming existing models in sentence ordering and translation tasks.

Contribution

It presents a novel recursive neural network approach that incorporates entity information for Chinese discourse coherence modeling, addressing limitations of previous feature-based methods.

Findings

Significantly outperforms baseline models in coherence tasks

Effectively captures entity overlaps across sentences

Improves Chinese discourse coherence evaluation accuracy

Abstract

Chinese discourse coherence modeling remains a challenge taskin Natural Language Processing field.Existing approaches mostlyfocus on the need for feature engineering, whichadoptthe sophisticated features to capture the logic or syntactic or semantic relationships acrosssentences within a text.In this paper, we present an entity-drivenrecursive deep modelfor the Chinese discourse coherence evaluation based on current English discourse coherenceneural network model. Specifically, to overcome the shortage of identifying the entity(nouns) overlap across sentences in the currentmodel, Our combined modelsuccessfully investigatesthe entities information into the recursive neural network freamework.Evaluation results on both sentence ordering and machine translation coherence rating task show the effectiveness of the proposed model, which significantly outperforms the existing strong baseline.