A Comprehensive Attempt to Research Statement Generation
This addresses a time-consuming task for researchers, but it is incremental as it builds on existing techniques like topic modeling and neural summarization.
The paper tackles the problem of automating research statement generation by proposing a new task and constructing a dataset with 62 statements and 1,203 publications, and their method outperforms baselines with improved content coverage and coherence.
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.