On the Effectiveness of the Pooling Methods for Biomedical Relation Extraction with Deep Learning

TL;DR

This paper evaluates various pooling methods in deep learning models for biomedical relation extraction, finding dependency-based pooling to be the most effective and achieving state-of-the-art results on benchmark datasets.

Contribution

It provides a comprehensive comparison of pooling strategies in biomedical relation extraction, identifying the most effective pooling method.

Findings

Dependency-based pooling outperforms other strategies.

Achieves state-of-the-art performance on benchmark datasets.

Provides guidance for selecting pooling methods in biomedical RE.

Abstract

Deep learning models have achieved state-of-the-art performances on many relation extraction datasets. A common element in these deep learning models involves the pooling mechanisms where a sequence of hidden vectors is aggregated to generate a single representation vector, serving as the features to perform prediction for RE. Unfortunately, the models in the literature tend to employ different strategies to perform pooling for RE, leading to the challenge to determine the best pooling mechanism for this problem, especially in the biomedical domain. In order to answer this question, in this work, we conduct a comprehensive study to evaluate the effectiveness of different pooling mechanisms for the deep learning models in biomedical RE. The experimental results suggest that dependency-based pooling is the best pooling strategy for RE in the biomedical domain, yielding the state-of-the-art performance on two benchmark datasets for this problem.