EXPR at SemEval-2018 Task 9: A Combined Approach for Hypernym Discovery

Proceedings of the 12th International Workshop on Semantic Evaluation (SemEval-2018), pages 919–923 New Orleans, Louisiana, June 5–6, 2018. ©2018 Association for Computational Linguistics EXPR at SemEval-2018 Task 9: A Combined Approach for Hypernym Discovery Ahmad Issa Alaa Aldine1,3, Mounira Harzallah2 Berio Giuseppe1, Nicolas B´echet1, Ahmad Faour3 1 IRISA - University Bretagne Sud, France 2 LINA - University of Nantes, France, 3 Lebanese University, Lebanon ahmad.issa-alaa-eddine@univ-ubs.fr mounira.harzallah@univ-nantes.fr, giuseppe.berio@univ-ubs.fr nicolas.bechet@irisa.fr, ahmad.faour@ul.edu.lb Abstract In this paper, we present our proposed sys- tem (EXPR) to participate in the hypernym discovery task of SemEval 2018. The task addresses the challenge of discovering hyper- nym relations from a text corpus. Our pro- posal is a combined approach of path-based technique and distributional technique. We use dependency parser on a corpus to extract can- didate hypernyms and represent their depen- dency paths as a feature vector. The feature vector is concatenated with a feature vector obtained using Wikipedia pre-trained term em- bedding model. The concatenated feature vec- tor fits a supervised machine learning method to learn a classifier model. This model is able to classify new candidate hypernyms as hyper- nym or not. Our system performs well to dis- cover new hypernyms not defined in gold hy- pernyms. 1 Introduction Hypernymy is an important lexical-semantic rela- tion that is useful for many applications such as question answering, machine translation, informa- tion retrieval, and so on. In addition, hypernym relations are the backbone for building ontologies. Various methods have been proposed to detect hypernym relation from text corpora. Most of these techniques are either path-based techniques or distributional techniques. In path-based meth- ods, the detection of hypernym relations is based on the lexico-syntactic paths connecting a pair of terms in a corpus. Conversely, distributional meth- ods are based on the distribution of term pair con- texts. Most of these methods were unsupervised. Recently, focus shifted towards supervised meth- ods. This task inherits complexity and is far from be- ing solved. The SemEval organizers address the same task but with a novel formulation (Camacho- Collados et al., 2018). They reformulate the task from hypernym detection into hypernym discov- ery. This novel formulation makes the task more realistic in terms of actual downstream applica- tion, while also enabling the benefits of informa- tion retrieval evaluation metrics. Hypernym de- tection focuses on deciding whether a hypernymic relation holds between a given pair of terms or not. Hypernym discovery focuses on discovering a set containing the best hypernyms for a given term from a given vocabulary search space. The task is divided into two subtasks: General-Purpose Hypernym Discovery and Domain-Specific Hy- pernym Discovery. The first consists of discov- ering hypernym in a general-purpose corpus, thus the SemEval organizers provide the participants with data for three languages: English, Italian, and Spanish. The second consists of discovering hypernym in a domain-specific corpus, thus they provide the participants with data for two specific domains: Medical and Music. The data contains a list of training terms along with gold hypernyms, a list of testing terms, and …

Content truncated to 500 words