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
APA
Vancouver
Author
Bibtex
}
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