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

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 2751–2800 of 10752 papers

TitleStatusHype
OkwuGbé: End-to-End Speech Recognition for Fon and Igbo—0
Modeling Context With Linear Attention for Scalable Document-Level Translation—0
Echo-Attention: Attend Once and Get N Attentions for Free—0
ODE Transformer: An Ordinary Differential Equation-Inspired Model for Sequence Generation—0
Evaluation of Transfer Learning for Polish with a text-to-text model—0
A Two-Stage Curriculum Training Framework for NMT—0
Alleviating the Inequality of Attention Heads for Neural Machine Translation—0
Towards Making the Most of Multilingual Pretraining for Zero-Shot Neural Machine TranslationCode1
Unifying Cross-lingual Summarization and Machine Translation with Compression RateCode0
Alternative Input Signals Ease Transfer in Multilingual Machine Translation—0
Breaking Down Multilingual Machine Translation—0
Why don't people use character-level machine translation?—0
Tricks for Training Sparse Translation Models—0
Multilingual Neural Machine Translation:Can Linguistic Hierarchies Help?—0
Non-Autoregressive Translation with Layer-Wise Prediction and Deep SupervisionCode1
Understanding Model Robustness to User-generated Noisy TextsCode0
Bandits Don't Follow Rules: Balancing Multi-Facet Machine Translation with Multi-Armed Bandits—0
Well-classified Examples are Underestimated in Classification with Deep Neural NetworksCode1
Semantics-aware Attention Improves Neural Machine Translation—0
MSP: Multi-Stage Prompting for Making Pre-trained Language Models Better TranslatorsCode1
Leveraging Automated Unit Tests for Unsupervised Code Translation—0
Systematic Inequalities in Language Technology Performance across the World's LanguagesCode0
Doubly-Trained Adversarial Data Augmentation for Neural Machine TranslationCode0
Learning Compact Metrics for MTCode1
LightSeq2: Accelerated Training for Transformer-based Models on GPUsCode2
Evaluation of Abstractive Summarisation Models with Machine Translation in Deliberative Processes—0
SRU++: Pioneering Fast Recurrence with Attention for Speech Recognition—0
WeTS: A Benchmark for Translation SuggestionCode1
Using Document Similarity Methods to create Parallel Datasets for Code Translation—0
It is Not as Good as You Think! Evaluating Simultaneous Machine Translation on Interpretation DataCode0
Unsupervised Neural Machine Translation with Generative Language Models Only—0
Disentangled Sequence to Sequence Learning for Compositional GeneralizationCode0
Towards a Unified View of Parameter-Efficient Transfer LearningCode1
Machine Translation Verbosity Control for Automatic Dubbing—0
Taming Sparsely Activated Transformer with Stochastic ExpertsCode1
On Neurons Invariant to Sentence Structural Changes in Neural Machine TranslationCode0
On the Privacy Risks of Deploying Recurrent Neural Networks in Machine Learning Models—0
The Low-Resource Double Bind: An Empirical Study of Pruning for Low-Resource Machine TranslationCode0
ABC: Attention with Bounded-memory Control—0
Spell my name: keyword boosted speech recognition—0
Sequence-to-Sequence Lexical Normalization with Multilingual Transformers—0
8-bit Optimizers via Block-wise QuantizationCode3
Building the Language Resource for a Cebuano-Filipino Neural Machine Translation System—0
On the Complementarity between Pre-Training and Back-Translation for Neural Machine TranslationCode1
Sicilian Translator: A Recipe for Low-Resource NMTCode0
Music Playlist Title Generation: A Machine-Translation Approach—0
Improving Zero-shot Multilingual Neural Machine Translation for Low-Resource Languages—0
Identify Bilingual Patterns and Phrases from a Bilingual Sentence Pair—0
Sentiment-Aware Measure (SAM) for Evaluating Sentiment Transfer by Machine Translation Systems—0
Prose2Poem: The Blessing of Transformers in Translating Prose to Persian PoetryCode0
Show:102550
← PrevPage 56 of 216Next →
All datasetsWMT2014 English-GermanWMT2014 English-FrenchIWSLT2014 German-EnglishACESWMT2016 English-RomanianWMT2016 Romanian-EnglishWMT2014 German-EnglishIWSLT2015 German-EnglishWMT2016 English-GermanIWSLT2015 English-VietnameseIWSLT2015 English-GermanWMT2016 German-English

Benchmark Results

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