A Comprehensive Attempt to Research Statement Generation

TL;DR

This paper introduces the research statement generation task to assist researchers in summarizing their work, involving dataset creation, method development, and evaluation, with a practical approach combining topic modeling and neural summarization.

Contribution

It presents the first comprehensive attempt at research statement generation, including a new dataset and a hybrid method for extracting relevant research achievements.

Findings

Our method outperforms baselines in content coverage.

The approach achieves better coherence in generated statements.

Experimental results validate the effectiveness of the proposed method.

Abstract

For a researcher, writing a good research statement is crucial but costs a lot of time and effort. To help researchers, in this paper, we propose the research statement generation (RSG) task which aims to summarize one's research achievements and help prepare a formal research statement. For this task, we conduct a comprehensive attempt including corpus construction, method design, and performance evaluation. First, we construct an RSG dataset with 62 research statements and the corresponding 1,203 publications. Due to the limitation of our resources, we propose a practical RSG method which identifies a researcher's research directions by topic modeling and clustering techniques and extracts salient sentences by a neural text summarizer. Finally, experiments show that our method outperforms all the baselines with better content coverage and coherence.