Multi-phase Word Sense Embedding Learning Using a Corpus and a Lexical Ontology

Word embeddings play a significant role in many modern NLP systems. However, most prevalent word embedding learning methods learn one representation per word which is problematic for polysemous words and homonymous words. To address this problem, we propose a multi-phase word sense embedding learning method which utilizes both a corpus and a lexical ontology to learn one embedding per word sense. We use word sense definitions and relations between word senses defined in a lexical ontology in a different way from existing systems. Experimental results on word similarity task show that our approach produces word sense embeddings of high quality.