SOTAVerified

Machine Translation

Machine translation is the task of translating a sentence in a source language to a different target language.

Approaches for machine translation can range from rule-based to statistical to neural-based. More recently, encoder-decoder attention-based architectures like BERT have attained major improvements in machine translation.

One of the most popular datasets used to benchmark machine translation systems is the WMT family of datasets. Some of the most commonly used evaluation metrics for machine translation systems include BLEU, METEOR, NIST, and others.

( Image credit: Google seq2seq )

Papers

Showing 49515000 of 10752 papers

TitleStatusHype
Transfer Learning for Algorithm Recommendation0
On the Importance of Word Boundaries in Character-level Neural Machine TranslationCode0
Mapping Supervised Bilingual Word Embeddings from English to low-resource languagesCode0
Estimating post-editing effort: a study on human judgements, task-based and reference-based metrics of MT qualityCode0
Transformers without Tears: Improving the Normalization of Self-AttentionCode0
Stabilizing Transformers for Reinforcement LearningCode1
From the Paft to the Fiiture: a Fully Automatic NMT and Word Embeddings Method for OCR Post-CorrectionCode0
Context-Gated ConvolutionCode0
Multilingual Question Answering from Formatted Text applied to Conversational Agents0
On the adequacy of untuned warmup for adaptive optimizationCode0
Novel Applications of Factored Neural Machine Translation0
One-To-Many Multilingual End-to-end Speech Translation0
An Interactive Machine Translation Framework for Modernizing Historical Documents0
Read, Highlight and Summarize: A Hierarchical Neural Semantic Encoder-based ApproachCode0
Improving Neural Machine Translation Robustness via Data Augmentation: Beyond Back Translation0
Overcoming the Rare Word Problem for Low-Resource Language Pairs in Neural Machine Translation0
On Leveraging the Visual Modality for Neural Machine Translation0
Domain Differential Adaptation for Neural Machine TranslationCode0
Adversarial reconstruction for Multi-modal Machine Translation0
Human Action Sequence Classification0
Compositional Generalization for Primitive SubstitutionsCode0
On Dimensional Linguistic Properties of the Word Embedding SpaceCode0
How Transformer Revitalizes Character-based Neural Machine Translation: An Investigation on Japanese-Vietnamese Translation SystemsCode0
Modeling Confidence in Sequence-to-Sequence Models0
Neural Zero-Inflated Quality Estimation Model For Automatic Speech Recognition System0
Improving Word Embedding Factorization for Compression Using Distilled Nonlinear Neural Decomposition0
Spatio-Temporal Fusion Based Convolutional Sequence Learning for Lip Reading0
Auto-Sizing the Transformer Network: Improving Speed, Efficiency, and Performance for Low-Resource Machine TranslationCode0
SlowMo: Improving Communication-Efficient Distributed SGD with Slow MomentumCode0
Multilingual End-to-End Speech Translation0
Application of Low-resource Machine Translation Techniques to Russian-Tatar Language Pair0
Better Document-Level Machine Translation with Bayes' Rule0
Machine Translation for Machines: the Sentiment Classification Use Case0
When and Why is Document-level Context Useful in Neural Machine Translation?Code0
A Survey of Methods to Leverage Monolingual Data in Low-resource Neural Machine Translation0
Grammatical Error Correction in Low-Resource ScenariosCode0
Regressing Word and Sentence Embeddings for Regularization of Neural Machine Translation0
Revisiting Self-Training for Neural Sequence GenerationCode0
Interrogating the Explanatory Power of Attention in Neural Machine TranslationCode0
Named Entity Recognition System for Sindhi Language0
The Source-Target Domain Mismatch Problem in Machine Translation0
In-training Matrix Factorization for Parameter-frugal Neural Machine Translation0
On the use of BERT for Neural Machine Translation0
Monotonic Multihead AttentionCode1
Improving Pre-Trained Multilingual Models with Vocabulary Expansion0
Large-scale Pretraining for Neural Machine Translation with Tens of Billions of Sentence Pairs0
Attention Forcing for Sequence-to-sequence Model Training0
Selecting Artificially-Generated Sentences for Fine-Tuning Neural Machine Translation0
Self-Induced Curriculum Learning in Neural Machine Translation0
Enhancing Attention with Explicit Phrasal Alignments0
Show:102550
← PrevPage 100 of 216Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1Transformer Cycle (Rev)BLEU score35.14Unverified
2Noisy back-translationBLEU score35Unverified
3Transformer+Rep(Uni)BLEU score33.89Unverified
4T5-11BBLEU score32.1Unverified
5BiBERTBLEU score31.26Unverified
6Transformer + R-DropBLEU score30.91Unverified
7Bi-SimCutBLEU score30.78Unverified
8BERT-fused NMTBLEU score30.75Unverified
9Data Diversification - TransformerBLEU score30.7Unverified
10SimCutBLEU score30.56Unverified
#ModelMetricClaimedVerifiedStatus
1Transformer+BT (ADMIN init)BLEU score46.4Unverified
2Noisy back-translationBLEU score45.6Unverified
3mRASP+Fine-TuneBLEU score44.3Unverified
4Transformer + R-DropBLEU score43.95Unverified
5Transformer (ADMIN init)BLEU score43.8Unverified
6AdminBLEU score43.8Unverified
7BERT-fused NMTBLEU score43.78Unverified
8MUSE(Paralllel Multi-scale Attention)BLEU score43.5Unverified
9T5BLEU score43.4Unverified
10Local Joint Self-attentionBLEU score43.3Unverified
#ModelMetricClaimedVerifiedStatus
1PiNMTBLEU score40.43Unverified
2BiBERTBLEU score38.61Unverified
3Bi-SimCutBLEU score38.37Unverified
4Cutoff + Relaxed Attention + LMBLEU score37.96Unverified
5DRDABLEU score37.95Unverified
6Transformer + R-Drop + CutoffBLEU score37.9Unverified
7SimCutBLEU score37.81Unverified
8Cutoff+KneeBLEU score37.78Unverified
9CutoffBLEU score37.6Unverified
10CipherDAugBLEU score37.53Unverified
#ModelMetricClaimedVerifiedStatus
1HWTSC-Teacher-SimScore19.97Unverified
2MS-COMET-22Score19.89Unverified
3MS-COMET-QE-22Score19.76Unverified
4KG-BERTScoreScore17.28Unverified
5metricx_xl_DA_2019Score17.17Unverified
6COMET-QEScore16.8Unverified
7COMET-22Score16.31Unverified
8UniTE-srcScore15.68Unverified
9UniTE-refScore15.38Unverified
10metricx_xxl_DA_2019Score15.24Unverified