Methods › General › Self-Supervised Learning › CRISS

CRISS

3 papers tagged archive 2025-07-28

Introduced by Chau Tran et al. in Cross-lingual Retrieval for Iterative Self-Supervised Training

archive 2025-07-28 Description, source and code snippet are the archive's method entry.

CRISS, or Cross-lingual Retrievial for Iterative Self-Supervised Training (CRISS), is a self-supervised learning method for multilingual sequence generation. CRISS is developed based on the finding that the encoder outputs of multilingual denoising autoencoder can be used as language agnostic representation to retrieve parallel sentence pairs, and training the model on these retrieved sentence pairs can further improve its sentence retrieval and translation capabilities in an iterative manner. Using only unlabeled data from many different languages, CRISS iteratively mines for parallel sentences across languages, trains a new better multilingual model using these mined sentence pairs, mines again for better parallel sentences, and repeats.

Paper Source

Papers archive 2025-07-28

3 shown of 3, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.

Towards Making the Most of Multilingual Pretraining for Zero-Shot Neural Machine Translation
16 Oct 2021 · 1 repository · arXiv:2110.08547

Syntology ran 2 of 2 samples · 0 unverified · 2 pointer-only (licence)
Zero-shot Cross-lingual Transfer of Neural Machine Translation with Multilingual Pretrained Encoders
18 Apr 2021 · 1 repository · arXiv:2104.08757

Syntology ran 1 of 1 samples · 0 unverified · 1 pointer-only (licence)
Cross-lingual Retrieval for Iterative Self-Supervised Training
16 Jun 2020 · 1 repository · arXiv:2006.09526

Tasks archive 2025-07-28

13 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.

Task	Papers
Machine Translation	3
Translation	3
Cross-Lingual Transfer	2
Decoder	2
NMT	2
Abstractive Text Summarization	1
Cross-Lingual Abstractive Summarization	1
Retrieval	1
Sentence	1
Sentence Retrieval	1
Unsupervised Machine Translation	1
XLM-R	1
Zero-Shot Cross-Lingual Transfer	1

Usage over time archive 2025-07-28

Papers per year the archive tags with this method, by the paper's archive date (3 dated). Bars are counts, not a trend claim.

Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).

Categories archive 2025-07-28

Self-Supervised Learning

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections