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 64016450 of 10752 papers

TitleStatusHype
Tree Structured Dirichlet Processes for Hierarchical Morphological SegmentationCode0
What we need to learn if we want to do and not just talk0
Unsupervised Detection of Metaphorical Adjective-Noun Pairs0
Marian: Cost-effective High-Quality Neural Machine Translation in C++Code0
Context-aware Cascade Attention-based RNN for Video Emotion Recognition0
Anaphora and Coreference Resolution: A Review0
Distilling Knowledge for Search-based Structured PredictionCode0
Deep Learning under Privileged Information Using Heteroscedastic DropoutCode0
Bi-Directional Neural Machine Translation with Synthetic Parallel Data0
Graph-based Filtering of Out-of-Vocabulary Words for Encoder-Decoder ModelsCode0
Inducing Grammars with and for Neural Machine Translation0
A Stochastic Decoder for Neural Machine Translation0
Theory and Experiments on Vector Quantized AutoencodersCode0
Reliability and Learnability of Human Bandit Feedback for Sequence-to-Sequence Reinforcement LearningCode0
Geometric Understanding of Deep Learning0
Japanese Predicate Conjugation for Neural Machine Translation0
Refining Source Representations with Relation Networks for Neural Machine Translation0
Context-Aware Neural Machine Translation Learns Anaphora Resolution0
Recursive Neural Network Based Preordering for English-to-Japanese Machine Translation0
Phrase Table as Recommendation Memory for Neural Machine Translation0
Mixed-Precision Training for NLP and Speech Recognition with OpenSeq2SeqCode0
Zero-Shot Dual Machine TranslationCode0
Filtering and Mining Parallel Data in a Joint Multilingual Space0
Hyperbolic Attention Networks0
Fast Neural Machine Translation Implementation0
Bilingual Sentiment Embeddings: Joint Projection of Sentiment Across LanguagesCode0
Meta-Learning for Low-Resource Neural Machine Translation0
Selecting Machine-Translated Data for Quick Bootstrapping of a Natural Language Understanding System0
Discrete Structural Planning for Neural Machine Translation0
How much does a word weigh? Weighting word embeddings for word sense induction0
Echo: Compiler-based GPU Memory Footprint Reduction for LSTM RNN Training0
Sparse and Constrained Attention for Neural Machine TranslationCode0
Combining Advanced Methods in Japanese-Vietnamese Neural Machine TranslationCode0
SNU_IDS at SemEval-2018 Task 12: Sentence Encoder with Contextualized Vectors for Argument Reasoning ComprehensionCode0
Metric for Automatic Machine Translation Evaluation based on Universal Sentence Representations0
Semantic Relatedness for All (Languages): A Comparative Analysis of Multilingual Semantic Relatedness Using Machine Translation0
Are BLEU and Meaning Representation in Opposition?0
Towards Robust Neural Machine Translation0
Token-level and sequence-level loss smoothing for RNN language modelsCode0
Bianet: A Parallel News Corpus in Turkish, Kurdish and English0
Bag-of-Words as Target for Neural Machine TranslationCode0
Triangular Architecture for Rare Language Translation0
Deep RNNs Encode Soft Hierarchical Syntax0
Leveraging Grammar and Reinforcement Learning for Neural Program Synthesis0
Bootstrapping Multilingual Intent Models via Machine Translation for Dialog Automation0
Neural Machine Translation for Bilingually Scarce Scenarios: A Deep Multi-task Learning Approach0
Deep Neural Machine Translation with Weakly-Recurrent UnitsCode0
Automatic Estimation of Simultaneous Interpreter PerformanceCode0
First Experiments with Neural Translation of Informal to Formal Mathematics0
On the Limitations of Unsupervised Bilingual Dictionary Induction0
Show:102550
← PrevPage 129 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
5AdminBLEU score43.8Unverified
6Transformer (ADMIN init)BLEU 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