A Survey of Cross-lingual Word Embedding Models

Research output: Contribution to journal › Journal article › Research › peer-review

Standard

A Survey of Cross-lingual Word Embedding Models. / Ruder, Sebastian; Vulić, Ivan; Søgaard, Anders.

In: The Journal of Artificial Intelligence Research, Vol. 65, 2019, p. 569-631.

Research output: Contribution to journal › Journal article › Research › peer-review

Harvard

Ruder, S, Vulić, I & Søgaard, A 2019, 'A Survey of Cross-lingual Word Embedding Models', The Journal of Artificial Intelligence Research, vol. 65, pp. 569-631. https://doi.org/10.1613/jair.1.11640

APA

Ruder, S., Vulić, I., & Søgaard, A. (2019). A Survey of Cross-lingual Word Embedding Models. The Journal of Artificial Intelligence Research, 65, 569-631. https://doi.org/10.1613/jair.1.11640

Vancouver

Ruder S, Vulić I, Søgaard A. A Survey of Cross-lingual Word Embedding Models. The Journal of Artificial Intelligence Research. 2019;65:569-631. https://doi.org/10.1613/jair.1.11640

Author

Ruder, Sebastian ; Vulić, Ivan ; Søgaard, Anders. / A Survey of Cross-lingual Word Embedding Models. In: The Journal of Artificial Intelligence Research. 2019 ; Vol. 65. pp. 569-631.

Bibtex

@article{fea6daf3e7534403929e5503cfc2a9a1,
title = "A Survey of Cross-lingual Word Embedding Models",
abstract = "Cross-lingual representations of words enable us to reason about word meaning in multilingual contexts and are a key facilitator of cross-lingual transfer when developing natural language processing models for low-resource languages. In this survey, we provide a comprehensive typology of cross-lingual word embedding models. We compare their data requirements and objective functions. The recurring theme of the survey is that many of the models presented in the literature optimize for the same objectives, and that seemingly different models are often equivalent, modulo optimization strategies, hyper-parameters, and such. We also discuss the different ways cross-lingual word embeddings are evaluated, as well as future challenges and research horizons.",
author = "Sebastian Ruder and Ivan Vuli{\'c} and Anders S{\o}gaard",
year = "2019",
doi = "10.1613/jair.1.11640",
language = "English",
volume = "65",
pages = "569--631",
journal = "Journal of Artificial Intelligence Research",
issn = "1076-9757",
publisher = "A A A I Press",

}

RIS

TY - JOUR

T1 - A Survey of Cross-lingual Word Embedding Models

AU - Ruder, Sebastian

AU - Vulić, Ivan

AU - Søgaard, Anders

PY - 2019

Y1 - 2019

N2 - Cross-lingual representations of words enable us to reason about word meaning in multilingual contexts and are a key facilitator of cross-lingual transfer when developing natural language processing models for low-resource languages. In this survey, we provide a comprehensive typology of cross-lingual word embedding models. We compare their data requirements and objective functions. The recurring theme of the survey is that many of the models presented in the literature optimize for the same objectives, and that seemingly different models are often equivalent, modulo optimization strategies, hyper-parameters, and such. We also discuss the different ways cross-lingual word embeddings are evaluated, as well as future challenges and research horizons.

AB - Cross-lingual representations of words enable us to reason about word meaning in multilingual contexts and are a key facilitator of cross-lingual transfer when developing natural language processing models for low-resource languages. In this survey, we provide a comprehensive typology of cross-lingual word embedding models. We compare their data requirements and objective functions. The recurring theme of the survey is that many of the models presented in the literature optimize for the same objectives, and that seemingly different models are often equivalent, modulo optimization strategies, hyper-parameters, and such. We also discuss the different ways cross-lingual word embeddings are evaluated, as well as future challenges and research horizons.

U2 - 10.1613/jair.1.11640

DO - 10.1613/jair.1.11640

M3 - Journal article

VL - 65

SP - 569

EP - 631

JO - Journal of Artificial Intelligence Research

JF - Journal of Artificial Intelligence Research

SN - 1076-9757

ER -

ID: 240408487