Automated Mining of Leaderboards for Empirical AI Research

TL;DR

This paper introduces an automated method using transformer models to efficiently extract and construct Leaderboards from scholarly texts, significantly improving the organization of empirical AI research data.

Contribution

It presents a novel approach employing transformer models for automated Leaderboard extraction, achieving state-of-the-art performance and enabling better organization of AI research.

Findings

Transformer models outperform baselines with over 90% F1 score.

The approach significantly accelerates Leaderboard construction.

It facilitates organizing empirical AI research in digital libraries.

Abstract

With the rapid growth of research publications, empowering scientists to keep oversight over the scientific progress is of paramount importance. In this regard, the Leaderboards facet of information organization provides an overview on the state-of-the-art by aggregating empirical results from various studies addressing the same research challenge. Crowdsourcing efforts like PapersWithCode among others are devoted to the construction of Leaderboards predominantly for various subdomains in Artificial Intelligence. Leaderboards provide machine-readable scholarly knowledge that has proven to be directly useful for scientists to keep track of research progress. The construction of Leaderboards could be greatly expedited with automated text mining. This study presents a comprehensive approach for generating Leaderboards for knowledge-graph-based scholarly information organization. Specifically, we investigate the problem of automated Leaderboard construction using state-of-the-art transformer models, viz. Bert, SciBert, and XLNet. Our analysis reveals an optimal approach that significantly outperforms existing baselines for the task with evaluation scores above 90% in F1. This, in turn, offers new state-of-the-art results for Leaderboard extraction. As a result, a vast share of empirical AI research can be organized in the next-generation digital libraries as knowledge graphs.