AI Paper Atlas

Research map / Benchmarks / WMT16 Ro-En

WMT16 Ro-En leaderboard

23 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on WMT16 Ro-En. Best BLEU: 39.1 (BERT-fused model + back translation, ICLR 2020).

Numbers are as each paper reports them, read by AI from its results tables and not checked by hand. Papers can differ in setting (training data, model size, extra data); the topic column shows what each paper is about. Open the paper before you compare or quote a number.

WMT16 Ro-En · BLEU

23 papers, each with its best reported number for its own method; higher is better.

#BLEU ↑MethodPaperTopic
139.1BERT-fused model + back translation
Transformer + back translation
Incorporating BERT into Neural Machine Translation
ICLR 2020 · Table: BLEU scores of WMT'16 R
Recognition and long-tail
238.83IOT (N=4)
Transformer
IOT: Instance-wise Layer Reordering for Transformer Structures
ICLR 2021 · Table: WMT14 En→De and WMT16 R
Attention and transformers
337.6CRISS Iter 3
mBART
Cross-lingual Retrieval for Iterative Self-Supervised Training
NeurIPS 2020 · Unsupervised machine translati
Self-supervised and contrastive
435.63AB-Net
bert-base-multilingual-cased; bert-base-uncased
Incorporating BERT into Parallel Sequence Decoding with Adapters
NeurIPS 2020 · Table 1
Attention and transformers
535.1Hard fusion
Transformer
Understanding and Improving Encoder Layer Fusion in Sequence-to-Sequence Learning
ICLR 2021 · Table: Results of the proposed
Attention and transformers
634.95CTC w/ NMLA + beam&lm
CTC w/ NMLA
Non-Monotonic Latent Alignments for CTC-Based Non-Autoregressive Machine Translation
NeurIPS 2022 · Table 2
Recognition and long-tail
734.82AMOM
CMLM
AMOM: Adaptive Masking over Masking for Conditional Masked Language Model
AAAI 2023 · Table 1
Attention and transformers
834.6CTC w/ DSLP & Mixed Training
CTC
Non-autoregressive Translation with Layer-Wise Prediction and Deep Supervision
AAAI 2022 · Table 1
RNNs and normalization
934.03NMLA w/ rephraser
NMLA
Rephrasing the Reference for Non-autoregressive Machine Translation
AAAI 2023 · Table 1
RNNs and normalization
1034.03duplex REDER
REDER
Duplex Sequence-to-Sequence Learning for Reversible Machine Translation
NeurIPS 2021 · Table 1
RNNs and normalization
13 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

Not affiliated with any conference, journal or the benchmark's authors. Corrections: contact@latenticlabs.com.