A Flexible Shallow Approach to Text Generation

TL;DR

This paper proposes a flexible, shallow text generation method that enhances adaptability for report generation tasks by linking domain and linguistic ontologies, moving beyond traditional reusable components and templates.

Contribution

It introduces a shallow, flexible approach to text generation that emphasizes domain-specific ontologies for quick adaptation, improving over existing template and component methods.

Findings

Effective for report generation with limited linguistic variation

Supports quick adaptation to new domains and tasks

Outperforms traditional template-based approaches

Abstract

In order to support the efficient development of NL generation systems, two orthogonal methods are currently pursued with emphasis: (1) reusable, general, and linguistically motivated surface realization components, and (2) simple, task-oriented template-based techniques. In this paper we argue that, from an application-oriented perspective, the benefits of both are still limited. In order to improve this situation, we suggest and evaluate shallow generation methods associated with increased flexibility. We advise a close connection between domain-motivated and linguistic ontologies that supports the quick adaptation to new tasks and domains, rather than the reuse of general resources. Our method is especially designed for generating reports with limited linguistic variations.