Learning principled bilingual mappings of word embeddings while preserving monolingual invariance

• DOI: 10.18653/v1/d16-1250
• Publication Date: 2016-12-30T08:17:50Z
• Authors: Mikel Artetxe; Gorka Labaka; Eneko Agirre
• Keywords: 0202 electrical engineering, electronic engineering, information engineering; 02 engineering and technology

Mapping word embeddings of different languages into a single space has multiple applications.In order to map from source target space, common approach is learn linear mapping that minimizes the distances between equivalences listed in bilingual dictionary.In this paper, we propose framework generalizes previous work, provides an efficient exact method optimal transformation and yields best results translation induction while preserving monolingual performance analogy task.