Multilingual Factor Analysis

Francisco Vargas; Kamen Brestnichki; Alex Papadopoulos-Korfiatis; Nils Hammerla

doi:10.18653/v1/P19-1170

Back to publications

Multilingual Factor Analysis

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

Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, 2019.

Abstract

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.

Links

Cite this Paper

BibTeX


@InProceedings{publications/multilingual-factor-analysis,
  title = 	 {Multilingual Factor Analysis},
  author = 	 {Vargas, Francisco and Brestnichki, Kamen and Papadopoulos-Korfiatis, Alex and Hammerla, Nils},
  booktitle = 	 {Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics},
  year = 	 {2019},
  doi = 	 {10.18653/v1/P19-1170},
  pdf = 	 {https://aclanthology.org/P19-1170.pdf},
  url = 	 {/publications/multilingual-factor-analysis.html},
  abstract = 	 {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.}
}

Endnote

%0 Conference Paper
%T Multilingual Factor Analysis
%A Francisco Vargas
%A Kamen Brestnichki
%A Alex Papadopoulos-Korfiatis
%A Nils Hammerla
%B Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
%D 2019	
%F publications/multilingual-factor-analysis
%R 10.18653/v1/P19-1170
%U /publications/multilingual-factor-analysis.html
%X 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.

RIS


TY  - CPAPER
TI  - Multilingual Factor Analysis
AU  - Francisco Vargas
AU  - Kamen Brestnichki
AU  - Alex Papadopoulos-Korfiatis
AU  - Nils Hammerla
BT  - Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
DA  - 2019/07/28	
ID  - publications/multilingual-factor-analysis
DO  - 10.18653/v1/P19-1170
L1  - https://aclanthology.org/P19-1170.pdf
UR  - /publications/multilingual-factor-analysis.html
AB  - 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.
ER  -

APA


Vargas, F., Brestnichki, K., Papadopoulos-Korfiatis, A. & Hammerla, N.. (2019). Multilingual Factor Analysis. Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics doi:10.18653/v1/P19-1170 Available from /publications/multilingual-factor-analysis.html.