Effective Strategies in Zero-Shot Neural Machine Translation
Not on the map. Why?
Abstract (arXiv)
In this paper, we proposed two strategies which can be applied to a multilingual neural machine translation system in order to better tackle zero-shot scenarios despite not having any parallel corpus. The experiments show that they are effective in terms of both performance and computing resources, especially in multilingual translation of unbalanced data in real zero-resourced condition when they alleviate the language bias problem.
Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). First posted on arXiv 21 Nov 2017.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 5; 2022: 0; 2023: 1.
6 papers.
- 2021Neural Machine Translation for Low-Resource Languages: A Surveycited by 109
- 2021Contrastive Learning for Many-to-many Multilingual Neural Machine Translationcited by 108
- 2021Low-Resource Neural Machine Translation for Southern African Languagescited by 7
- 2021Zero-shot Speech Translationcited by 5
- 2023Accurate Knowledge Distillation with n-best Rerankingcited by 4
- 2021Unsupervised Transfer Learning in Multilingual Neural Machine Translation with Cross-Lingual Word Embeddingscited by 1
- 2023Accurate Knowledge Distillation with n-best Reranking20 May 2023
- 2021Zero-shot Speech Translation13 Jul 2021
- 2021Neural Machine Translation for Low-Resource Languages: A Survey29 Jun 2021
- 2021Contrastive Learning for Many-to-many Multilingual Neural Machine Translation20 May 2021
- 2021Low-Resource Neural Machine Translation for Southern African Languages1 Apr 2021
- 2021Unsupervised Transfer Learning in Multilingual Neural Machine Translation with Cross-Lingual Word Embeddings11 Mar 2021