Fine-Grained Chemical Entity Typing with Multimodal Knowledge Representation

TL;DR

This paper introduces a new benchmark dataset and a multi-modal learning framework for fine-grained chemical entity typing, leveraging chemical structures and cross-modal attention to improve extraction accuracy from complex chemistry literature.

Contribution

The paper presents a novel multi-modal approach and a new dataset for fine-grained chemical entity typing, addressing challenges of complex names and graphic representations.

Findings

The proposed framework outperforms existing methods.

The CHEMET dataset facilitates research in chemical entity typing.

Multi-modal learning improves representation of chemical entities.

Abstract

Automated knowledge discovery from trending chemical literature is essential for more efficient biomedical research. How to extract detailed knowledge about chemical reactions from the core chemistry literature is a new emerging challenge that has not been well studied. In this paper, we study the new problem of fine-grained chemical entity typing, which poses interesting new challenges especially because of the complex name mentions frequently occurring in chemistry literature and graphic representation of entities. We introduce a new benchmark data set (CHEMET) to facilitate the study of the new task and propose a novel multi-modal representation learning framework to solve the problem of fine-grained chemical entity typing by leveraging external resources with chemical structures and using cross-modal attention to learn effective representation of text in the chemistry domain. Experiment results show that the proposed framework outperforms multiple state-of-the-art methods.