Domain Controlled Title Generation with Human Evaluation

TL;DR

This paper introduces a domain-controlled title generation method for scientific articles using a pre-trained transformer and local vocabulary sampling, achieving titles that are realistic, relevant, and comparable to human-generated titles.

Contribution

The paper presents a novel approach employing domain-specific token sampling with a transformer model for automatic title generation, enhancing relevance and quality.

Findings

Generated titles scored higher on ROUGE metrics than original titles.

Human evaluation rated machine-generated titles as acceptable across multiple parameters.

Titles closely linked to abstracts, improving relevance and catchiness.

Abstract

We study automatic title generation and present a method for generating domain-controlled titles for scientific articles. A good title allows you to get the attention that your research deserves. A title can be interpreted as a high-compression description of a document containing information on the implemented process. For domain-controlled titles, we used the pre-trained text-to-text transformer model and the additional token technique. Title tokens are sampled from a local distribution (which is a subset of global vocabulary) of the domain-specific vocabulary and not global vocabulary, thereby generating a catchy title and closely linking it to its corresponding abstract. Generated titles looked realistic, convincing, and very close to the ground truth. We have performed automated evaluation using ROUGE metric and human evaluation using five parameters to make a comparison between human and machine-generated titles. The titles produced were considered acceptable with higher metric ratings in contrast to the original titles. Thus we concluded that our research proposes a promising method for domain-controlled title generation.