Extracting Biomolecular Interactions Using Semantic Parsing of Biomedical Text

TL;DR

This paper improves biomolecular interaction extraction by using deep semantic representations, extending to document-level predictions, and combining semantic and syntactic structures for more robust results.

Contribution

It introduces the use of Abstract Meaning Representations for better accuracy, extends extraction to document-level, and combines semantic and syntactic features via a graph kernel framework.

Findings

AMR significantly improves extraction accuracy

Document-level predictions increase consistency

Combining semantic and syntactic features enhances robustness

Abstract

We advance the state of the art in biomolecular interaction extraction with three contributions: (i) We show that deep, Abstract Meaning Representations (AMR) significantly improve the accuracy of a biomolecular interaction extraction system when compared to a baseline that relies solely on surface- and syntax-based features; (ii) In contrast with previous approaches that infer relations on a sentence-by-sentence basis, we expand our framework to enable consistent predictions over sets of sentences (documents); (iii) We further modify and expand a graph kernel learning framework to enable concurrent exploitation of automatically induced AMR (semantic) and dependency structure (syntactic) representations. Our experiments show that our approach yields interaction extraction systems that are more robust in environments where there is a significant mismatch between training and test conditions.