Neural Net Models for Open-Domain Discourse Coherence

Understand

Discourse coherence is strongly associated with text quality, making it important to natural language generation and understanding.

• Yet existing models of coherence focus on measuring individual aspects of coherence (lexical overlap, rhetorical structure, entity centering) in narrow domains.
• In this paper, we describe domain-independent neural models of discourse coherence that are capable of measuring multiple aspects of coherence in existing sentences and can maintain coherence while generating new sentences.
• We study both discriminative models that learn to distinguish coherent from incoherent discourse, and generative models that produce coherent text, including a novel neural latent-variable Markovian generative model that captures the latent discourse dependencies between sentences in a text.