Dataset Mention Extraction in Scientific Articles Using Bi-LSTM-CRF Model

TL;DR

This paper presents a neural network approach using Bi-LSTM-CRF architecture to automatically extract dataset mentions from scientific articles, aiming to improve tracking and citation of datasets in research.

Contribution

It introduces a novel neural network model specifically designed for dataset mention extraction in scientific texts, demonstrating high accuracy on social science articles.

Findings

Achieved F1 score of 0.885 on social science dataset

Highlights limitations of current datasets and suggests future improvements

Provides a foundation for automated dataset citation tracking

Abstract

Datasets are critical for scientific research, playing an important role in replication, reproducibility, and efficiency. Researchers have recently shown that datasets are becoming more important for science to function properly, even serving as artifacts of study themselves. However, citing datasets is not a common or standard practice in spite of recent efforts by data repositories and funding agencies. This greatly affects our ability to track their usage and importance. A potential solution to this problem is to automatically extract dataset mentions from scientific articles. In this work, we propose to achieve such extraction by using a neural network based on a Bi-LSTM-CRF architecture. Our method achieves F1 = 0.885 in social science articles released as part of the Rich Context Dataset. We discuss the limitations of the current datasets and propose modifications to the model to be done in the future.