Deriving a Representative Vector for Ontology Classes with Instance Word Vector Embeddings

Abstract

Selecting a representative vector for a set of vectors is a very common requirement in many algorithmic tasks. Traditionally, the mean or median vector is selected. Ontology classes are sets of homogeneous instance objects that can be converted to a vector space by word vector embeddings. This study proposes a methodology to derive a representative vector for ontology classes whose instances were converted to the vector space. We start by deriving five candidate vectors which are then used to train a machine learning model that would calculate a representative vector for the class. We show that our methodology out-performs the traditional mean and median vector representations.

References in corpus (1)

• Sentiment Analysis of Citations Using Word2vec

Cited by in corpus (7)

• Synergistic Union of Word2Vec and Lexicon for Domain Specific Semantic Similarity
• Ontology Embedding: A Survey of Methods, Applications and Resources
• SigmaLaw-ABSA: Dataset for Aspect-Based Sentiment Analysis in Legal Opinion Texts
• Identifying Relationships Among Sentences in Court Case Transcripts Using Discourse Relations
• Rule-Based Approach for Party-Based Sentiment Analysis in Legal Opinion Texts
• Shift-of-Perspective Identification Within Legal Cases
• DeepVisInterests: CNN-Ontology Prediction of Users Interests from Social Images