SEAL: Scientific Keyphrase Extraction and Classification

TL;DR

SEAL is a neural and machine learning-based tool designed for automatic extraction and classification of scientific keyphrases, significantly improving over existing methods and supporting scholarly tasks.

Contribution

Introduces SEAL, combining a neural extraction module with a Random Forest classifier for effective scientific keyphrase extraction and classification.

Findings

SEAL outperforms multiple state-of-the-art baselines

The system demonstrates robustness across various datasets

Significant improvement in keyphrase extraction accuracy

Abstract

Automatic scientific keyphrase extraction is a challenging problem facilitating several downstream scholarly tasks like search, recommendation, and ranking. In this paper, we introduce SEAL, a scholarly tool for automatic keyphrase extraction and classification. The keyphrase extraction module comprises two-stage neural architecture composed of Bidirectional Long Short-Term Memory cells augmented with Conditional Random Fields. The classification module comprises of a Random Forest classifier. We extensively experiment to showcase the robustness of the system. We evaluate multiple state-of-the-art baselines and show a significant improvement. The current system is hosted at http://lingo.iitgn.ac.in:5000/.