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 61516200 of 10752 papers

TitleStatusHype
Construction of a Multilingual Corpus Annotated with Translation Relations0
Monolingual and Cross-lingual Zero-shot Style Transfer0
Low-Latency Neural Speech Translation0
Effective Parallel Corpus Mining using Bilingual Sentence Embeddings0
Active Learning for Interactive Neural Machine Translation of Data Streams0
Doubly Attentive Transformer Machine Translation0
Training Neural Machine Translation using Word Embedding-based Loss0
NMT-based Cross-lingual Document Embeddings0
Back-Translation-Style Data Augmentation for End-to-End ASR0
Auto-Encoding Variational Neural Machine TranslationCode0
Finding Better Subword Segmentation for Neural Machine TranslationCode0
"Bilingual Expert" Can Find Translation ErrorsCode0
Cross-lingual Argumentation Mining: Machine Translation (and a bit of Projection) is All You Need!Code0
Otem&Utem: Over- and Under-Translation Evaluation Metric for NMTCode0
Inductive Visual Localisation: Factorised Training for Superior Generalisation0
A Hand-Held Multimedia Translation and Interpretation System with Application to Diet Management0
Recurrent Stacking of Layers for Compact Neural Machine Translation Models0
Generating Synthetic Data for Neural Keyword-to-Question Models0
Linear Transformations for Cross-lingual Semantic Textual Similarity0
Universal TransformersCode0
Latent Alignment and Variational AttentionCode0
NMT-Keras: a Very Flexible Toolkit with a Focus on Interactive NMT and Online Learning0
Learning The Sequential Temporal Information with Recurrent Neural Networks0
Testing Untestable Neural Machine Translation: An Industrial Case0
Natural Language Processing for Information ExtractionCode0
A Concept Specification and Abstraction-based Semantic Representation: Addressing the Barriers to Rule-based Machine Translation0
Diversity in Machine Learning0
A Neural Approach to Language Variety Translation0
Model-Level Dual Learning0
Fine-Grained Discourse Structures in Continuation Semantics0
A Context-aware Convolutional Natural Language Generation model for Dialogue Systems0
Constructing a Lexicon of English Discourse Connectives0
Recognizing Emotions in Video Using Multimodal DNN Feature Fusion0
Neural Machine Translation Techniques for Named Entity TransliterationCode0
Exploiting Common Characters in Chinese and Japanese to Learn Cross-Lingual Word Embeddings via Matrix Factorization0
Multimodal Neural Machine Translation for Low-resource Language Pairs using Synthetic Data0
Multilingual Seq2seq Training with Similarity Loss for Cross-Lingual Document Classification0
A Hybrid Learning Scheme for Chinese Word Embedding0
Unsupervised Source Hierarchies for Low-Resource Neural Machine Translation0
Enhancement of Encoder and Attention Using Target Monolingual Corpora in Neural Machine Translation0
OpenNMT System Description for WNMT 2018: 800 words/sec on a single-core CPU0
Named-Entity Tagging and Domain adaptation for Better Customized Translation0
Document-Level Adaptation for Neural Machine Translation0
Multi-glance Reading Model for Text Understanding0
Low-Resource Machine Transliteration Using Recurrent Neural Networks of Asian Languages0
NEWS 2018 Whitepaper0
Baseline: A Library for Rapid Modeling, Experimentation and Development of Deep Learning Algorithms targeting NLPCode0
Texar: A Modularized, Versatile, and Extensible Toolbox for Text Generation0
Report of NEWS 2018 Named Entity Transliteration Shared Task0
Transliteration Better than Translation? Answering Code-mixed Questions over a Knowledge Base0
Show:102550
← PrevPage 124 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