AI Paper Atlas

Research map / Benchmarks / WMT14 EN-DE newstest2014

WMT14 EN-DE newstest2014 leaderboard

12 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on WMT14 EN-DE newstest2014. Best BLEU: 32.56 (Ours + back-translation, AAAI 2022).

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.

WMT14 EN-DE newstest2014 · BLEU

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

#BLEU ↑MethodPaperTopic
132.56Ours + back-translation
mBERT
Deep Fusing Pre-trained Models into Neural Machine Translation
AAAI 2022 · Table 4
Pruning and efficient tuning
230.7Data Diversification
Transformer
Data Diversification: A Simple Strategy For Neural Machine Translation
NeurIPS 2020 · text
RNNs and normalization
330.2Transformer + LayerDrop
Transformer Big
Reducing Transformer Depth on Demand with Structured Dropout
ICLR 2020 · Table 1
Attention and transformers
429.37BBFNMT (big)
Transformer (big)
Explicit Sentence Compression for Neural Machine Translation
AAAI 2020 · Table: Comparison with existin
Attention and transformers
529.33GRET-Big
Transformer-Big
GRET: Global Representation Enhanced Transformer
AAAI 2020 · Table 4
Attention and transformers
628.89Transformer-Big + Context-Aware SANs
Transformer-Big
Context-Aware Self-Attention Networks
AAAI 2019 · Main results table
Attention and transformers
728.4Transformer (big)Attention is All you Need
NeurIPS 2017 · Table 2
Attention and transformers
827.32LevT with sequence-level interpolation
AT-base
Understanding Knowledge Distillation in Non-autoregressive Machine Translation
ICLR 2020 · Table: Results w/ and w/o sequ
RNNs and normalization
926.7SAU
Transformer
SAU: Smooth Activation Function Using Convolution with Approximate Identities
ECCV 2022 · Table 7
RNNs and normalization
1026.03MoE with 2048 ExpertsOutrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer
ICLR 2017 · Table, WMT'14 En→De
Mixture of experts
2 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.