Towards a Universal Semantic Dictionary

• Main Authors: Maria Jose Castro-Bleda, Eszter Iklódi, Gábor Recski, Gábor Borbély
• Format: Article
• Language: English
• Published: MDPI AG 2019-09-01
• Series: Applied Sciences
• Subjects: natural language processing; semantics; word embeddings; multilingual embeddings; translation; artificial neural networks
• Online Access: https://www.mdpi.com/2076-3417/9/19/4060

A novel method for finding linear mappings among word embeddings for several languages, taking as pivot a shared, multilingual embedding space, is proposed in this paper. Previous approaches learned translation matrices between two specific languages, while this method learns translation matrices between a given language and a shared, multilingual space. The system was first trained on bilingual, and later on multilingual corpora as well. In the first case, two different training data were applied: Dinu’s English−Italian benchmark data, and English−Italian translation pairs extracted from the PanLex database. In the second case, only the PanLex database was used. The system performs on English−Italian languages with the best setting significantly better than the baseline system given by Mikolov, and it provides a comparable performance with more sophisticated systems. Exploiting the richness of the PanLex database, the proposed method makes it possible to learn linear mappings among an arbitrary number of languages.