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 4151–4200 of 10752 papers

TitleStatusHype
CEF Data Marketplace: Powering a Long-term Supply of Language Data—0
Exploring Coreference Features in Heterogeneous Data—0
Neural Machine Translation between similar South-Slavic languages—0
The AFRL WMT20 News Translation Systems—0
How Should Markup Tags Be Translated?Code0
The University of Maryland’s Submissions to the WMT20 Chat Translation Task: Searching for More Data to Adapt Discourse-Aware Neural Machine Translation—0
Neural Machine Translation for Similar Languages: The Case of Indo-Aryan Languages—0
Multilingual Neural Machine Translation: Case-study for Catalan, Spanish and Portuguese Romance Languages—0
Evaluation of Machine Translation Methods applied to Medical Terminologies—0
OPPO’s Machine Translation Systems for WMT20—0
Simultaneous Translation—0
Losing Heads in the Lottery: Pruning Transformer Attention in Neural Machine Translation—0
Evaluating the usefulness of neural machine translation for the Polish translators in the European Commission—0
Improving Parallel Data Identification using Iteratively Refined Sentence Alignments and Bilingual Mappings of Pre-trained Language Models—0
Looking inside Noun Compounds: Unsupervised Prepositional and Free Paraphrasing—0
NICT Kyoto Submission for the WMT’20 Quality Estimation Task: Intermediate Training for Domain and Task Adaptation—0
NICE: Neural Integrated Custom Engines—0
Monolingual Adapters for Zero-Shot Neural Machine Translation—0
PosEdiOn: Post-Editing Assessment in PythOn—0
Estimation vs Metrics: is QE Useful for MT Model Selection?—0
Progress of the PRINCIPLE Project: Promoting MT for Croatian, Icelandic, Irish and Norwegian—0
OCR, Classification & Machine Translation (OCCAM)—0
Transformer-based Neural Machine Translation System for Hindi – Marathi: WMT20 Shared Task—0
How do LSPs compute MT discounts? Presenting a company’s pipeline and its use—0
A human evaluation of English-Irish statistical and neural machine translation—0
The NITS-CNLP System for the Unsupervised MT Task at WMT 2020—0
MT for subtitling: User evaluation of post-editing productivity—0
Towards a Better Evaluation of Metrics for Machine Translation—0
Log-Linear Reformulation of the Noisy Channel Model for Document-Level Neural Machine Translation—0
Improving Word Sense Disambiguation with Translations—0
Active Learning Approaches to Enhancing Neural Machine Translation—0
An Overview of the SEBAMAT Project—0
Infosys Machine Translation System for WMT20 Similar Language Translation Task—0
ELITR: European Live Translator—0
Low-Resource Unsupervised NMT: Diagnosing the Problem and Providing a Linguistically Motivated SolutionCode0
Effectively pretraining a speech translation decoder with Machine Translation data—0
A3-108 Machine Translation System for Similar Language Translation Shared Task 2020—0
QRev: Machine Translation of User Reviews: What Influences the Translation Quality?—0
Multi-Agent Mutual Learning at Sentence-Level and Token-Level for Neural Machine Translation—0
Ixamed’s submission description for WMT20 Biomedical shared task: benefits and limitations of using terminologies for domain adaptation—0
NMT based Similar Language Translation for Hindi - Marathi—0
Hybrid Emoji-Based Masked Language Models for Zero-Shot Abusive Language Detection—0
The University of Edinburgh’s English-Tamil and English-Inuktitut Submissions to the WMT20 News Translation Task—0
IIE’s Neural Machine Translation Systems for WMT20—0
Domain Informed Neural Machine Translation: Developing Translation Services for Healthcare Enterprise—0
The ADAPT System Description for the WMT20 News Translation Task—0
Document Level NMT of Low-Resource Languages with Backtranslation—0
Document-level Neural MT: A Systematic Comparison—0
Document-Level Machine Translation Evaluation Project: Methodology, Effort and Inter-Annotator Agreement—0
Huawei’s Submissions to the WMT20 Biomedical Translation Task—0
Show:102550
← PrevPage 84 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