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 85018550 of 10752 papers

TitleStatusHype
A Dynamic Programming Algorithm for Computing N-gram Posteriors from Lattices0
Leave-one-out Word Alignment without Garbage Collector Effects0
Detecting Content-Heavy Sentences: A Cross-Language Case Study0
Learning Semantic Composition to Detect Non-compositionality of Multiword Expressions0
Dependency Graph-to-String Translation0
An Empirical Comparison Between N-gram and Syntactic Language Models for Word Ordering0
Visual Bilingual Lexicon Induction with Transferred ConvNet Features0
Automatic Diacritics Restoration for Hungarian0
A Discriminative Training Procedure for Continuous Translation Models0
Investigating Continuous Space Language Models for Machine Translation Quality Estimation0
Intra-sentential Zero Anaphora Resolution using Subject Sharing Recognition0
Syntax-based Rewriting for Simultaneous Machine Translation0
A Comparison between Count and Neural Network Models Based on Joint Translation and Reordering Sequences0
Improving Statistical Machine Translation with a Multilingual Paraphrase Database0
Improving Semantic Parsing with Enriched Synchronous Context-Free Grammar0
Improving fast\_align by Reordering0
A Binarized Neural Network Joint Model for Machine Translation0
Improving Arabic Diacritization through Syntactic Analysis0
Improved Arabic Dialect Classification with Social Media Data0
Human Evaluation of Grammatical Error Correction Systems0
How to Avoid Unwanted Pregnancies: Domain Adaptation using Neural Network Models0
Hierarchical Phrase-based Stream Decoding0
Hierarchical Latent Words Language Models for Robust Modeling to Out-Of Domain Tasks0
Hierarchical Incremental Adaptation for Statistical Machine Translation0
Hierarchical Back-off Modeling of Hiero Grammar based on Non-parametric Bayesian Model0
A Coarse-Grained Model for Optimal Coupling of ASR and SMT Systems for Speech Translation0
Consistency-Aware Search for Word Alignment0
Graph-Based Collective Lexical Selection for Statistical Machine Translation0
Variable-Length Word Encodings for Neural Translation Models0
Touch-Based Pre-Post-Editing of Machine Translation Output0
Search-Aware Tuning for Hierarchical Phrase-based Decoding0
Generalized Agreement for Bidirectional Word Alignment0
Rule Selection with Soft Syntactic Features for String-to-Tree Statistical Machine Translation0
Compact, Efficient and Unlimited Capacity: Language Modeling with Compressed Suffix Trees0
Neural Machine Translation of Rare Words with Subword UnitsCode1
Auto-Sizing Neural Networks: With Applications to n-gram Language Models0
Probabilistic Modelling of Morphologically Rich Languages0
Effective Approaches to Attention-based Neural Machine TranslationCode1
Depth-Gated LSTM0
Removing Biases from Trainable MT Metrics by Using Self-Training0
Adapting Phrase-based Machine Translation to Normalise Medical Terms in Social Media Messages0
Feature-based Decipherment for Large Vocabulary Machine Translation0
Improve the Evaluation of Fluency Using Entropy for Machine Translation Evaluation Metrics0
An Automatic Machine Translation Evaluation Metric Based on Dependency Parsing Model0
Zero Alignment of Verb Arguments in a Parallel Treebank0
Targeted Paraphrasing on Deep Syntactic Layer for MT Evaluation0
Cross-Lingual Dependency Parsing with Universal Dependencies and Predicted PoS Labels0
Using Parallel Texts and Lexicons for Verbal Word Sense Disambiguation0
Classifying informative and imaginative prose using complex networks0
Classifier-Based Text Simplification for Improved Machine Translation0
Show:102550
← PrevPage 171 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