Global alignment for relation extraction in Microbiology

TL;DR

This paper presents a global alignment method combined with syntactic information for relation extraction in microbiology texts, demonstrating competitive or superior performance to LSTM models on two relation extraction tasks.

Contribution

Introduces a global alignment approach integrated with syntactic features for relation extraction, offering an alternative to neural network models in microbiology.

Findings

Performance comparable or better than LSTM on two RE tasks

Effective use of syntactic information in relation extraction

Potential for simpler models with competitive accuracy

Abstract

We investigate a method to extract relations from texts based on global alignment and syntactic information. Combined with SVM, this method is shown to have a performance comparable or even better than LSTM on two RE tasks.