Cross-lingual Word Embeddings beyond Zero-shot Machine Translation

Research output: Working paper › Preprint › Research

Standard

Cross-lingual Word Embeddings beyond Zero-shot Machine Translation. / Chen, Shifei; Basirat, Ali.

2020.

Research output: Working paper › Preprint › Research

Harvard

Chen, S & Basirat, A 2020 'Cross-lingual Word Embeddings beyond Zero-shot Machine Translation'.

APA

Chen, S., & Basirat, A. (2020). Cross-lingual Word Embeddings beyond Zero-shot Machine Translation.

Vancouver

Chen S, Basirat A. Cross-lingual Word Embeddings beyond Zero-shot Machine Translation. 2020 Nov 3.

Author

Chen, Shifei ; Basirat, Ali. / Cross-lingual Word Embeddings beyond Zero-shot Machine Translation. 2020.

Bibtex

@techreport{258f2dd9f44b40c98efe43092bfffdae,
title = "Cross-lingual Word Embeddings beyond Zero-shot Machine Translation",
abstract = " We explore the transferability of a multilingual neural machine translation model to unseen languages when the transfer is grounded solely on the cross-lingual word embeddings. Our experimental results show that the translation knowledge can transfer weakly to other languages and that the degree of transferability depends on the languages' relatedness. We also discuss the limiting aspects of the multilingual architectures that cause weak translation transfer and suggest how to mitigate the limitations. ",
keywords = "cs.CL",
author = "Shifei Chen and Ali Basirat",
note = "Accepted at the 8th Swedish Language Technology Conference (SLTC-2020)",
year = "2020",
month = nov,
day = "3",
language = "Udefineret/Ukendt",
type = "WorkingPaper",

}

RIS

TY - UNPB

T1 - Cross-lingual Word Embeddings beyond Zero-shot Machine Translation

AU - Chen, Shifei

AU - Basirat, Ali

N1 - Accepted at the 8th Swedish Language Technology Conference (SLTC-2020)

PY - 2020/11/3

Y1 - 2020/11/3

N2 - We explore the transferability of a multilingual neural machine translation model to unseen languages when the transfer is grounded solely on the cross-lingual word embeddings. Our experimental results show that the translation knowledge can transfer weakly to other languages and that the degree of transferability depends on the languages' relatedness. We also discuss the limiting aspects of the multilingual architectures that cause weak translation transfer and suggest how to mitigate the limitations.

AB - We explore the transferability of a multilingual neural machine translation model to unseen languages when the transfer is grounded solely on the cross-lingual word embeddings. Our experimental results show that the translation knowledge can transfer weakly to other languages and that the degree of transferability depends on the languages' relatedness. We also discuss the limiting aspects of the multilingual architectures that cause weak translation transfer and suggest how to mitigate the limitations.

KW - cs.CL

M3 - Preprint

BT - Cross-lingual Word Embeddings beyond Zero-shot Machine Translation

ER -

ID: 366049090