Injecting Entity Types into Entity-Guided Text Generation

TL;DR

This paper introduces a novel neural text generation model that explicitly injects entity types during decoding, improving the coherence and relevance of generated content by leveraging entity information.

Contribution

The paper proposes a multi-step decoder that incorporates entity types into neural text generation, outperforming existing type embedding methods on news datasets.

Findings

Type injection improves generation quality over baselines

Model achieves higher coherence in entity mention generation

Experiments validate effectiveness on public news datasets

Abstract

Recent successes in deep generative modeling have led to significant advances in natural language generation (NLG). Incorporating entities into neural generation models has demonstrated great improvements by assisting to infer the summary topic and to generate coherent content. To enhance the role of entity in NLG, in this paper, we aim to model the entity type in the decoding phase to generate contextual words accurately. We develop a novel NLG model to produce a target sequence based on a given list of entities. Our model has a multi-step decoder that injects the entity types into the process of entity mention generation. Experiments on two public news datasets demonstrate type injection performs better than existing type embedding concatenation baselines.