UC3M-NII Team at SemEval-2018 Task 7: Semantic Relation Classification in Scientific Papers via Convolutional Neural Network

Proceedings of the 12th International Workshop on Semantic Evaluation (SemEval-2018), pages 793–797 New Orleans, Louisiana, June 5–6, 2018. ©2018 Association for Computational Linguistics UC3M-NII Team at SemEval-2018 Task 7: Semantic Relation Classification in Scientific Papers via Convolutional Neural Network V´ıctor Su´arez-Paniagua, Isabel Segura-Bedmar Computer Science Department Universidad Carlos III de Madrid Legan´es 28911, Madrid, Spain vspaniag,isegura@inf.uc3m.es Akiko Aizawa National Institute of Informatics 2-1-2 Hitotsubashi, Chiyoda-ku Tokyo, Japan aizawa@nii.ac.jp Abstract This paper reports our participation for SemEval-2018 Task 7 on extraction and clas- sification of relationships between entities in scientific papers. Our approach is based on the use of a Convolutional Neural Network (CNN) trained on 350 abstract with manually anno- tated entities and relations. Our hypothesis is that this deep learning model can be applied to extract and classify relations between en- tities for scientific papers at the same time. We use the Part-of-Speech and the distances to the target entities as part of the embedding for each word and we blind all the entities by marker names. In addition, we use sampling techniques to overcome the imbalance issues of this dataset. Our architecture obtained an F1-score of 35.4% for the relation extraction task and 18.5% for the relation classification task with a basic configuration of the one step CNN. 1 Introduction Nowadays, there is a high increase in the publica- tion of scientific articles every year, which demon- strates that we are living in an emerging knowl- edge era. Experts cannot deal with this explo- sion of information and it is very hard to be up to date about the state-of-the-art techniques in a given field. This arduous task could be reduced if we automatically identify concepts from scien- tific articles and recognize the semantic relations between them with Natural Language Processing (NLP) techniques. The Semantic Relation Extraction and Classifi- cation in Scientific Papers task at SemEval-2018 task 7 (G´abor et al., 2018) provides a framework for measuring the automatic annotation perfor- mance by models which are trained on scientific publications abstracts. The task defines six cate- gories of relations between concepts and two tasks are proposed: (1) the classification of the relations between two entities in the predefined categories, which is divided in two scenarios according to the data used: clean or noisy; and (2) the extraction of the relations given the entities from the clean data, which also could involve their subsequent classifi- cation. In this paper, we describe our participation for SemEval-2018 Task 7 on the extraction of rela- tionships between entities in scientific papers and also the subsequent classification in the predefined classes of this relations with one step classifier. The model is based on the Convolutional Neural Network (CNN) proposed in (Kim, 2014), which was the first work to exploit this architecture for the task of sentence classification. CNN is a ro- bust deep-learning architecture which has exhib- ited good performance in others NLP tasks such as semantic clustering (Wang et al., 2016), senti- ment analysis (Dos Santos and Gatti, 2014) and event detection …

Content truncated to 500 words