Abstractified Multi-instance Learning (AMIL) for Biomedical Relation Extraction

TL;DR

This paper introduces AMIL, a novel reformulation of multi-instance learning that abstracts biomedical entities into semantic types, improving relation extraction performance in noisy, long-tail biomedical datasets.

Contribution

The paper proposes a new abstractified multi-instance learning (AMIL) approach that enhances biomedical relation extraction by leveraging entity type abstraction and a novel embedding architecture.

Findings

AMIL outperforms traditional MIL in biomedical relation extraction.

Entity type abstraction reduces noise and improves model accuracy.

The proposed embedding architecture further boosts performance.

Abstract

Relation extraction in the biomedical domain is a challenging task due to a lack of labeled data and a long-tail distribution of fact triples. Many works leverage distant supervision which automatically generates labeled data by pairing a knowledge graph with raw textual data. Distant supervision produces noisy labels and requires additional techniques, such as multi-instance learning (MIL), to denoise the training signal. However, MIL requires multiple instances of data and struggles with very long-tail datasets such as those found in the biomedical domain. In this work, we propose a novel reformulation of MIL for biomedical relation extraction that abstractifies biomedical entities into their corresponding semantic types. By grouping entities by types, we are better able to take advantage of the benefits of MIL and further denoise the training signal. We show this reformulation, which we refer to as abstractified multi-instance learning (AMIL), improves performance in biomedical relationship extraction. We also propose a novel relationship embedding architecture that further improves model performance.