ClaiRE at SemEval-2018 Task 7 - Extended Version

TL;DR

This paper presents the extended results of ClaiRE, a system for classifying semantic relations in scientific literature, achieving improved F1 scores on clean and noisy datasets in SemEval-2018 Task 7.

Contribution

The paper introduces technical enhancements and post-evaluation improvements to the ClaiRE system for semantic relation classification in scientific texts.

Findings

F1 score of 75.11% on clean data

F1 score of 81.44% on noisy data

Enhanced preprocessing improved classification performance

Abstract

In this paper we describe our post-evaluation results for SemEval-2018 Task 7 on clas- sification of semantic relations in scientific literature for clean (subtask 1.1) and noisy data (subtask 1.2). This is an extended ver- sion of our workshop paper (Hettinger et al., 2018) including further technical details (Sec- tions 3.2 and 4.3) and changes made to the preprocessing step in the post-evaluation phase (Section 2.1). Due to these changes Classification of Relations using Embeddings (ClaiRE) achieved an improved F1 score of 75.11% for the first subtask and 81.44% for the second.