Multilingual Factor Analysis Article Swipe

PDF

Related Concepts

Computer science Latent variable Natural language processing Task (project management) Artificial intelligence Embedding Latent variable model Variety (cybernetics) Generative grammar Word (group theory) Generative model Variable (mathematics) Word embedding Meaning (existential) Factor (programming language) Space (punctuation) Speech recognition Linguistics Mathematics Psychology Economics Philosophy Psychotherapist Management Mathematical analysis Operating system Programming language

Francisco Vargas , Kamen Brestnichki , Alex Papadopoulos-Korfiatis , Nils Hammerla ·

YOU? · · 2019 · Open Access · · DOI: https://doi.org/10.18653/v1/p19-1170 · OA: W2946736944

In this work we approach the task of learning multilingual word representations in an offline manner by fitting a generative latent variable model to a multilingual dictionary. We model equivalent words in different languages as different views of the same word generated by a common latent variable representing their latent lexical meaning. We explore the task of alignment by querying the fitted model for multilingual embeddings achieving competitive results across a variety of tasks. The proposed model is robust to noise in the embedding space making it a suitable method for distributed representations learned from noisy corpora.