Scientific Relation Extraction with Selectively Incorporated Concept Embeddings

TL;DR

This paper presents an improved end-to-end scientific relation extraction model that incorporates selective concept embeddings, achieving top rankings in SemEval 2018 tasks.

Contribution

It introduces a character-level encoding attention mechanism for selecting pretrained concept embeddings in relation extraction.

Findings

Ranked second in relation classification

Ranked first in relation extraction

Demonstrated effectiveness of selective concept embeddings

Abstract

This paper describes our submission for the SemEval 2018 Task 7 shared task on semantic relation extraction and classification in scientific papers. We extend the end-to-end relation extraction model of (Miwa and Bansal) with enhancements such as a character-level encoding attention mechanism on selecting pretrained concept candidate embeddings. Our official submission ranked the second in relation classification task (Subtask 1.1 and Subtask 2 Senerio 2), and the first in the relation extraction task (Subtask 2 Scenario 1).