Cross-lingual Word Embeddings beyond Zero-shot Machine Translation
Research output: Working paper › Preprint › Research
Documents
- 2011.01682v1
94.1 KB, PDF document
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.
Original language | Undefined/Unknown |
---|---|
Publication status | Published - 3 Nov 2020 |
Externally published | Yes |
Bibliographical note
Accepted at the 8th Swedish Language Technology Conference (SLTC-2020)
ID: 366049090