SciREL at SemEval-2018 Task 7: A System for Semantic Relation Extraction and Classification

Proceedings of the 12th International Workshop on Semantic Evaluation (SemEval-2018), pages 853–857 New Orleans, Louisiana, June 5–6, 2018. ©2018 Association for Computational Linguistics SciREL at SemEval-2018 Task 7: A System for Semantic Relation Extraction and Classification Darshini Mahendran Chathurika S. Wickramasinghe Bridget T. McInnes Virginia Commonwealth University, Richmond, Virginia {mahendrand, brahmanacsw, btmcinnes}@vcu.edu Abstract This paper describes our system, SciREL (Sci- entific abstract RELation extraction system), developed for the SemEval 2018 Task 7: Se- mantic Relation Extraction and Classification in Scientific Papers. We present a feature- vector based system to extract explicit se- mantic relation and classify them. Our sys- tem is trained in the ACL corpus (Bird et al., 2008) that contains annotated abstracts given by the task organizers. When an abstract with annotated entities is given as the input into our system, it extracts the semantic relations through a set of defined features and classi- fies them into one of the given six categories of relations through feature engineering and a learned model. For the best combination of features our system SciREL obtained an F- measure of 20.03 on the official test corpus in the relation classification Subtask 1.1. In this paper, we provide an in-depth error analysis of our results to prevent duplication of research efforts in the development of future systems. 1 Introduction Automatic detection and extraction of semantic relations among the entities from unstructured text has received growing attention in the recent years (Konstantinova, 2014), (Augenstein et al., 2017), (Fundel et al., 2006), (Luo et al., 2016). Text mining is the process of automatically ex- tracting knowledge from unstructured text docu- ments and this idea of text mining is to link ex- tracted information together which possibly re- sults in new facts or hypothesis to be explored fur- ther through conventional scientific experimenta- tions (Delen and Crossland, 2008), (Fleuren and Alkema, 2015). SemEval 2018 Task 7 (G´abor et al., 2018) aims to extract and classify semantic relations to im- prove the access to scientific literature. Their tasks focus on identifying pairs of entities that are in- stances of six semantic relation types and classi- fying those instances into one of the six seman- tic relation types. To address this challenge, we implemented a supervised machine learning based approach in order to extract explicit semantic rela- tions from the ACL anthology corpus (Bird et al., 2008) for Subtask 1.1. 2 Methodology In this section, we describe our relation extraction system (SciREL) which classifies the semantic re- lations into one of the given six categories of rela- tions. The main steps of our approach can be sum- marized as follows. First, an abstract with anno- tated entities is given as the input into our system and all the sentences in the abstract are segmented, preprocessed, and the entity pairs are identified. Second, a set of features are defined and are com- bined into a feature vector which is used to train a machine learning model. This is the most cru- cial part of our system, as the idea …

Content truncated to 500 words