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 54515500 of 10752 papers

TitleStatusHype
Comparing Pipelined and Integrated Approaches to Dialectal Arabic Neural Machine Translation0
Neural Text Normalization with Subword Units0
A Robust Abstractive System for Cross-Lingual Summarization0
Understanding and Improving Hidden Representations for Neural Machine Translation0
Unsupervised Extraction of Partial Translations for Neural Machine Translation0
Language Learning and Processing in People and Machines0
MuST-C: a Multilingual Speech Translation Corpus0
Online Distilling from Checkpoints for Neural Machine Translation0
Measuring Immediate Adaptation Performance for Neural Machine Translation0
Word Embedding-Based Automatic MT Evaluation Metric using Word Position Information0
One Size Does Not Fit All: Comparing NMT Representations of Different Granularities0
Overcoming Catastrophic Forgetting During Domain Adaptation of Neural Machine Translation0
Improving Neural Machine Translation with Neural Syntactic Distance0
Improved Lexically Constrained Decoding for Translation and Monolingual Rewriting0
Highly Effective Arabic Diacritization using Sequence to Sequence Modeling0
Revisiting NMT for Normalization of Early English LettersCode0
Examining Structure of Word Embeddings with PCA0
Crowdsourcing and Validating Event-focused Emotion Corpora for German and English0
Thinking Slow about Latency Evaluation for Simultaneous Machine Translation0
DiaBLa: A Corpus of Bilingual Spontaneous Written Dialogues for Machine TranslationCode0
Unbabel's Submission to the WMT2019 APE Shared Task: BERT-based Encoder-Decoder for Automatic Post-Editing0
Interactive-predictive neural multimodal systems0
Unsupervised Paraphrasing without Translation0
A Generalized Framework of Sequence Generation with Application to Undirected Sequence ModelsCode0
Semantic Diversity by Phonetics for Accurate and Robust Machine Translation0
On Measuring Gender Bias in Translation of Gender-neutral PronounsCode0
Leap-LSTM: Enhancing Long Short-Term Memory for Text CategorizationCode0
Revisiting Low-Resource Neural Machine Translation: A Case StudyCode0
Levenshtein TransformerCode1
Gated Group Self-Attention for Answer Selection0
Exposure Bias versus Self-Recovery: Are Distortions Really Incremental for Autoregressive Text Generation?0
Soft Contextual Data Augmentation for Neural Machine TranslationCode0
A Call for Prudent Choice of Subword Merge Operations in Neural Machine Translation0
Debiasing Word Embeddings Improves Multimodal Machine Translation0
An Analysis of Source-Side Grammatical Errors in NMT0
Theme-aware generation model for chinese lyrics0
CDSA: Cross-Dimensional Self-Attention for Multivariate, Geo-tagged Time Series ImputationCode0
Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be PrunedCode1
Corpus Augmentation by Sentence Segmentation for Low-Resource Neural Machine Translation0
Improving Minimal Gated Unit for Sequential Data0
Towards Neural Decompilation0
Target Conditioned Sampling: Optimizing Data Selection for Multilingual Neural Machine Translation0
A Neural, Interactive-predictive System for Multimodal Sequence to Sequence TasksCode0
Multimodal Transformer with Multi-View Visual Representation for Image Captioning0
Guiding Inferences in Connection Tableau by Recurrent Neural NetworksCode0
A Case Study: Exploiting Neural Machine Translation to Translate CUDA to OpenCL0
Recovering Dropped Pronouns in Chinese Conversations via Modeling Their ReferentsCode0
REPLAB: A Reproducible Low-Cost Arm Benchmark Platform for Robotic Learning0
Joint Source-Target Self Attention with Locality ConstraintsCode0
Towards Interlingua Neural Machine Translation0
Show:102550
← PrevPage 110 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