Development of an Extractive Title Generation System Using Titles of Papers of Top Conferences for Intermediate English Students

TL;DR

This paper presents an extractive title generation system for intermediate English authors, utilizing keywords and BERT-based evaluation to improve the quality of academic paper titles.

Contribution

It introduces a novel extractive title generation system and an evaluation model trained on top-conference titles to assist less proficient English authors.

Findings

The evaluation model outperforms students in identifying top-conference titles.

The system effectively formulates titles from abstract keywords.

BERT-based training enhances title appropriateness assessment.

Abstract

The formulation of good academic paper titles in English is challenging for intermediate English authors (particularly students). This is because such authors are not aware of the type of titles that are generally in use. We aim to realize a support system for formulating more effective English titles for intermediate English and beginner authors. This study develops an extractive title generation system that formulates titles from keywords extracted from an abstract. Moreover, we realize a title evaluation model that can evaluate the appropriateness of paper titles. We train the model with titles of top-conference papers by using BERT. This paper describes the training data, implementation, and experimental results. The results show that our evaluation model can identify top-conference titles more effectively than intermediate English and beginner students.