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 6951–7000 of 10752 papers

TitleStatusHype
Sentiment Aware Neural Machine Translation—0
Sentiment Lexicons for Arabic Social Media—0
Sentiment Perception Adversarial Attacks on Neural Machine Translation Systems—0
Sentiment Preservation in Review Translation using Curriculum-based Re-inforcement Framework—0
SentSim: Crosslingual Semantic Evaluation of Machine Translation—0
Separating Grains from the Chaff: Using Data Filtering to Improve Multilingual Translation for Low-Resourced African Languages—0
Seq2seq for Morphological Reinflection: When Deep Learning Fails—0
Sequence-based Structured Prediction for Semantic Parsing—0
Sequence Generation: From Both Sides to the Middle—0
Sequence Length is a Domain: Length-based Overfitting in Transformer Models—0
Sequence Modeling using Gated Recurrent Neural Networks—0
Sequence Shortening for Context-Aware Machine Translation—0
Sequence-to-Dependency Neural Machine Translation—0
Sequence-to-Lattice Models for Fast Translation—0
Sequence-to-Sequence Lexical Normalization with Multilingual Transformers—0
Sequence to Sequence Mixture Model for Diverse Machine Translation—0
Sequence-to-Sequence Models with Attention Mechanistically Map to the Architecture of Human Memory Search—0
Sequence to Sequence Networks for Roman-Urdu to Urdu Transliteration—0
Sequence-to-Sequence Neural Net Models for Grapheme-to-Phoneme Conversion—0
Sequential Annotation and Chunking of Chinese Discourse Structure—0
SERF: Towards better training of deep neural networks using log-Softplus ERror activation Function—0
Service Composition Scenarios for Task-Oriented Translation—0
Set Generation Networks for End-to-End Knowledge Base Population—0
Set-Theoretic Alignment for Comparable Corpora—0
SG-Net: Syntax Guided Transformer for Language Representation—0
SG Translate Together - Uplifting Singapore’s translation standards with the community through technology—0
SHAKKIL: An Automatic Diacritization System for Modern Standard Arabic Texts—0
Shallow Convolutional Neural Network for Implicit Discourse Relation Recognition—0
Shallow Discourse Parsing for Under-Resourced Languages: Combining Machine Translation and Annotation Projection—0
Shallow Local Multi-Bottom-up Tree Transducers in Statistical Machine Translation—0
Shallow Semantically-Informed PBSMT and HPBSMT—0
Shared Latent Space by Both Languages in Non-Autoregressive Neural Machine Translation—0
Shared-Private Bilingual Word Embeddings for Neural Machine Translation—0
Shared Task Proposal: Multilingual Surface Realization Using Universal Dependency Trees—0
Shared Task Proposal: Syntactic Paraphrase Ranking—0
Share or Not? Learning to Schedule Language-Specific Capacity for Multilingual Translation—0
Sharing Attention Weights for Fast Transformer—0
Sharing resources between free/open-source rule-based machine translation systems: Grammatical Framework and Apertium—0
Sharing, Teaching and Aligning: Knowledgeable Transfer Learning for Cross-Lingual Machine Reading Comprehension—0
Shata-Anuvadak: Tackling Multiway Translation of Indian Languages—0
Sheffield at SemEval-2017 Task 9: Transition-based language generation from AMR.—0
Sheffield MultiMT: Using Object Posterior Predictions for Multimodal Machine Translation—0
Sheffield Submissions for the WMT18 Quality Estimation Shared Task—0
Sheffield Submissions for WMT18 Multimodal Translation Shared Task—0
Sheffield Systems for the English-Romanian WMT Translation Task—0
Sheffield Systems for the Finnish-English WMT Translation Task—0
SHEF-Lite 2.0: Sparse Multi-task Gaussian Processes for Translation Quality Estimation—0
SHEF-Lite: When Less is More for Translation Quality Estimation—0
SHEF-LIUM-NN: Sentence level Quality Estimation with Neural Network Features—0
SHEF-MIME: Word-level Quality Estimation Using Imitation Learning—0
Show:102550
← PrevPage 140 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