Identification of Tasks, Datasets, Evaluation Metrics, and Numeric Scores for Scientific Leaderboards Construction

TL;DR

This paper presents a framework that automatically extracts tasks, datasets, metrics, and scores from NLP research papers to facilitate the automatic creation of scientific leaderboards, addressing the challenge of tracking rapid research developments.

Contribution

The paper introduces a novel framework and datasets for automatic extraction of key research information, advancing the construction of scientific leaderboards in NLP.

Findings

Our model outperforms baselines significantly.

The framework successfully extracts key research components.

First step towards automatic leaderboard construction in NLP.

Abstract

While the fast-paced inception of novel tasks and new datasets helps foster active research in a community towards interesting directions, keeping track of the abundance of research activity in different areas on different datasets is likely to become increasingly difficult. The community could greatly benefit from an automatic system able to summarize scientific results, e.g., in the form of a leaderboard. In this paper we build two datasets and develop a framework (TDMS-IE) aimed at automatically extracting task, dataset, metric and score from NLP papers, towards the automatic construction of leaderboards. Experiments show that our model outperforms several baselines by a large margin. Our model is a first step towards automatic leaderboard construction, e.g., in the NLP domain.