ELiRF-UPV at SemEval-2018 Task 10: Capturing Discriminative Attributes with Knowledge Graphs and Wikipedia

Proceedings of the 12th International Workshop on Semantic Evaluation (SemEval-2018), pages 968–971 New Orleans, Louisiana, June 5–6, 2018. ©2018 Association for Computational Linguistics ELiRF-UPV at SemEval-2018 Task 10: Capturing Discriminative Attributes with Knowledge Graphs and Wikipedia Jos´e- ´Angel Gonz´alez, Llu´ıs-F. Hurtado, Encarna Segarra, Ferran Pla Universitat Polit`ecnica de Val`encia Cam´ı de Vera sn, 46022, Val`encia {jogonba2|lhurtado|esegarra|fpla}@dsic.upv.es Abstract This paper describes the participation of ELiRF-UPV team at task 10, Capturing Dis- criminative Attributes, of SemEval-2018. Our best approach consists of using ConceptNet, Wikipedia and NumberBatch embeddings in order to stablish relationships between con- cepts and attributes. Furthermore, this sys- tem achieves competitive results in the official evaluation. 1 Introduction Capturing Discriminative Attributes, task 10 of SemEval-2018 (Krebs et al., 2018), proposes working on semantic difference detection . The goal of the task is to predict whether a word is a discriminative attribute between two other words. This problem is known as semantic difference de- tection, which is a binary classification task: given a triple (apple, banana, red), it consists in de- termining whether it exemplifies a semantic dif- ference. Regarding semantic difference, it is a ternary relation between two concepts, for in- stance, (apple, banana) and a discriminative fea- ture (red) that characterizes the first concept but not the other. As task 10 is related to the semantic relations among different words, knowledge graphs seems the most appropriate resources to be used. An interesting knowledge resource that we used for this task is ConceptNet. In particular, Concept- Net (Speer et al., 2016) is a knowledge graph that connects words and phrases of natural language using labeled edges. It was designed to repre- sent some general knowledge involved in natu- ral language and could be used in combination with other resources. The combination of Con- ceptNet with distributed representations such as Word2Vec (Mikolov et al., 2013) and GloVe (Pen- nington et al., 2014), is known as NumberBatch embeddings (Speer et al., 2016). Regarding the relations specified in Concept- Net, there are a total of 36 relations such as IsA (A banana is a dessert), UsedFor (A net is used for catching fish), or FormOf (“Leaves” is a form of the word “leaf”), intended to represent a relation- ship independently of the language or the source of the terms it connects. In this work, we propose five knowledge based systems and one additional machine learning sys- tem based on Siamese networks. We used Con- ceptNet in order to determine if each input con- cept and the input attribute are related through a relation edge or path. When there is a relation- ship between the first concept and the attribute and there is no relationship between the second con- cept and the attribute, then the answer is 1, other- wise, the answer is 0. However, there are cases in which ConceptNet does not provide enough infor- mation to take a decision. In those cases, we have implemented a system that seeks the information in Wikipedia articles by using distances between NumberBatch embeddings. 2 Resources …

Content truncated to 500 words