Article
Version 1
Preserved in Portico This version is not peer-reviewed
Towards a Universal Semantic Dictionary
Version 1
: Received: 25 July 2019 / Approved: 29 July 2019 / Online: 29 July 2019 (11:05:16 CEST)
A peer-reviewed article of this Preprint also exists.
Castro-Bleda, M.J.; Iklódi, E.; Recski, G.; Borbély, G. Towards a Universal Semantic Dictionary. Appl. Sci. 2019, 9, 4060. Castro-Bleda, M.J.; Iklódi, E.; Recski, G.; Borbély, G. Towards a Universal Semantic Dictionary. Appl. Sci. 2019, 9, 4060.
Abstract
A novel method for finding linear mappings among word embeddings for several languages, taking as pivot a shared, universal embedding space, is proposed in this paper. Previous approaches learn translation matrices between two specific languages, but this method learn translation matrices between a given language and a shared, universal 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 of Mikolov et al. [1], and it provides a comparable performance with the more sophisticated systems of Faruqui and Dyer [2] and Dinu et al. [3]. Exploiting the richness of the PanLex database, the proposed method makes it possible to learn linear mappings among an arbitrary number of languages.
Keywords
natural language processing; semantics; word embeddings; multilingual embeddings; translation; artificial neural networks
Subject
Computer Science and Mathematics, Artificial Intelligence and Machine Learning
Copyright: This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Comments (0)
We encourage comments and feedback from a broad range of readers. See criteria for comments and our Diversity statement.
Leave a public commentSend a private comment to the author(s)
* All users must log in before leaving a comment
