mlsanityData to 14 Oct 2026

A Teacher-Student Framework for Zero-Resource Neural Machine Translation

arXiv 1705.00753 ↗First posted 2 May 2017cs.CLcited by 22

Not on the map. Why?

Abstract (arXiv)

While end-to-end neural machine translation (NMT) has made remarkable progress recently, it still suffers from the data scarcity problem for low-resource language pairs and domains. In this paper, we propose a method for zero-resource NMT by assuming that parallel sentences have close probabilities of generating a sentence in a third language. Based on this assumption, our method is able to train a source-to-target NMT model ("student") without parallel corpora available, guided by an existing pivot-to-target NMT model ("teacher") on a source-pivot parallel corpus. Experimental results show that the proposed method significantly improves over a baseline pivot-based model by +3.0 BLEU points across various language pairs.

Key facts. Cited by 22 papers in the map (data through 14 Oct 2026). First posted on arXiv 2 May 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2020: 1; 2021: 10; 2022: 3; 2023: 5; 2024: 1; 2025: 1; 2026: 1.

22 papers.

Sort:

By area:

  1. 2021Neural Machine Translation for Low-Resource Languages: A Surveycited by 109
  2. 2021Contrastive Learning for Many-to-many Multilingual Neural Machine Translationcited by 108
  3. 2020Autoregressive Knowledge Distillation through Imitation Learningcited by 74
  4. 2021Zero-shot Cross-lingual Transfer of Neural Machine Translation with Multilingual Pretrained Encoderscited by 24
  5. 2021Adapting High-resource NMT Models to Translate Low-resource Related Languages without Parallel Datacited by 17
  6. 2021A Survey on Low-Resource Neural Machine Translationcited by 16
  7. 2022UM4: Unified Multilingual Multiple Teacher-Student Model for Zero-Resource Neural Machine Translationcited by 10
  8. 2021Towards Making the Most of Multilingual Pretraining for Zero-Shot Neural Machine Translationcited by 8
  9. 2024AnyTrans: Translate AnyText in the Image with Large Scale Modelscited by 8
  10. 2021Token-wise Curriculum Learning for Neural Machine Translationcited by 4
  11. 2022ConsistTL: Modeling Consistency in Transfer Learning for Low-Resource Neural Machine Translationcited by 4
  12. 2023SCALE: Synergized Collaboration of Asymmetric Language Translation Enginescited by 3
10 more
  1. 2021Jointly Learning to Repair Code and Generate Commit Messagecited by 2
  2. 2023ZRIGF: An Innovative Multimodal Framework for Zero-Resource Image-Grounded Dialogue Generationcited by 2
  3. 2026KD4MT: A Survey of Knowledge Distillation for Machine Translationcited by 2
  4. 2021Self-Learning for Zero Shot Neural Machine Translationcited by 1
  5. 2025Multilingual Non-Autoregressive Machine Translation without Knowledge Distillationcited by 1
  6. 2021Improving Zero-shot Multilingual Neural Machine Translation for Low-Resource Languagescited by 0
  7. 2022Look Backward and Forward: Self-Knowledge Distillation with Bidirectional Decoder for Neural Machine Translationcited by 0
  8. 2023MSSRNet: Manipulating Sequential Style Representation for Unsupervised Text Style Transfercited by 0
  9. 2023Exploring Linguistic Similarity and Zero-Shot Learning for Multilingual Translation of Dravidian Languagescited by 0
  10. 2023Direct Neural Machine Translation with Task-level Mixture of Experts modelscited by 0