Method and Dataset Mining in Scientific Papers

TL;DR

This paper introduces MDER, a new entity recognition model for extracting methods and datasets from scientific papers, along with datasets from PAKDD conference papers, to enhance literature analysis in machine learning.

Contribution

The paper presents a novel entity recognition model, MDER, and constructs datasets for extracting methods and datasets from scientific papers, enabling better discipline analysis.

Findings

MDER achieves promising extraction performance

Mining results are visualized for better understanding

Constructed datasets facilitate further research

Abstract

Literature analysis facilitates researchers better understanding the development of science and technology. The conventional literature analysis focuses on the topics, authors, abstracts, keywords, references, etc., and rarely pays attention to the content of papers. In the field of machine learning, the involved methods (M) and datasets (D) are key information in papers. The extraction and mining of M and D are useful for discipline analysis and algorithm recommendation. In this paper, we propose a novel entity recognition model, called MDER, and constructe datasets from the papers of the PAKDD conferences (2009-2019). Some preliminary experiments are conducted to assess the extraction performance and the mining results are visualized.