Knowledge-guided Convolutional Networks for Chemical-Disease Relation Extraction

TL;DR

This paper introduces Knowledge-guided Convolutional Networks (KCN), a novel approach that leverages prior knowledge from structured databases to improve chemical-disease relation extraction from biomedical texts, achieving state-of-the-art results.

Contribution

The paper presents a new model that integrates knowledge representations into convolutional networks for enhanced relation extraction in biomedical text.

Findings

KCN achieves 71.28% F1-score on BioCreative V CDR dataset.

KCN outperforms most state-of-the-art systems.

Knowledge integration improves extraction performance.

Abstract

Background: Automatic extraction of chemical-disease relations (CDR) from unstructured text is of essential importance for disease treatment and drug development. Meanwhile, biomedical experts have built many highly-structured knowledge bases (KBs), which contain prior knowledge about chemicals and diseases. Prior knowledge provides strong support for CDR extraction. How to make full use of it is worth studying. Results: This paper proposes a novel model called "Knowledge-guided Convolutional Networks (KCN)" to leverage prior knowledge for CDR extraction. The proposed model first learns knowledge representations including entity embeddings and relation embeddings from KBs. Then, entity embeddings are used to control the propagation of context features towards a chemical-disease pair with gated convolutions. After that, relation embeddings are employed to further capture the weighted context features by a shared attention pooling. Finally, the weighted context features containing additional knowledge information are used for CDR extraction. Experiments on the BioCreative V CDR dataset show that the proposed KCN achieves 71.28% F1-score, which outperforms most of the state-of-the-art systems. Conclusions: This paper proposes a novel CDR extraction model KCN to make full use of prior knowledge. Experimental results demonstrate that KCN could effectively integrate prior knowledge and contexts for the performance improvement.