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 76017650 of 10752 papers

TitleStatusHype
Character-Aware Neural Networks for Arabic Named Entity Recognition for Social Media0
Parallel Sentence Compression0
Capturing Pragmatic Knowledge in Article Usage Prediction using LSTMs0
Semantically Motivated Hebrew Verb-Noun Multi-Word Expressions Identification0
Factored Neural Machine Translation Architectures0
Fast Collocation-Based Bayesian HMM Word Alignment0
Faster and Lighter Phrase-based Machine Translation Baseline0
Extending WordNet with Fine-Grained Collocational Information via Supervised Distributional Learning0
CATaLog Online: A Web-based CAT Tool for Distributed Translation with Data Capture for APE and Translation Process Research0
Fast Gated Neural Domain Adaptation: Language Model as a Case Study0
Adaptation and Combination of NMT Systems: The KIT Translation Systems for IWSLT 20160
FBK’s Neural Machine Translation Systems for IWSLT 20160
Exploring Distributional Representations and Machine Translation for Aspect-based Cross-lingual Sentiment Classification.0
The MITLL-AFRL IWSLT 2016 Systems0
Translation Using JAPIO Patent Corpora: JAPIO at WAT20160
Using Linguistic Data for English and Spanish Verb-Noun Combination Identification0
Universal Reordering via Linguistic Typology0
Towards Deep Learning in Hindi NER: An approach to tackle the Labelled Data Sparsity0
Twitter Named Entity Extraction and Linking Using Differential Evolution0
The IMAGACT4ALL Ontology of Animated Images: Implications for Theoretical and Machine Translation of Action Verbs from English-Indian Languages0
Topic-Informed Neural Machine Translation0
Verbframator:Semi-Automatic Verb Frame Annotator Tool with Special Reference to Marathi0
Verb sense disambiguation in Machine Translation0
Zero-resource Dependency Parsing: Boosting Delexicalized Cross-lingual Transfer with Linguistic Knowledge0
Using Bilingual Segments in Generating Word-to-word Translations0
Two-Step MT: Predicting Target Morphology0
The RWTH Aachen Machine Translation System for IWSLT 20160
UFAL Submissions to the IWSLT 2016 MT Track0
The UMD Machine Translation Systems at IWSLT 2016: English-to-French Translation of Speech Transcripts0
Unsupervised Stemmer for Arabic Tweets0
Using Ambiguity Detection to Streamline Linguistic Annotation0
Translationese: Between Human and Machine Translation0
What Makes Word-level Neural Machine Translation Hard: A Case Study on English-German Translation0
The IWSLT 2016 Evaluation Campaign0
A Simple, Fast Diverse Decoding Algorithm for Neural GenerationCode0
Kannada Spell Checker with Sandhi Splitter0
Neural Machine Translation with Latent Semantic of Image and Text0
False-Friend Detection and Entity Matching via Unsupervised Transliteration0
Neural Machine Translation with Pivot Languages0
Toward Multilingual Neural Machine Translation with Universal Encoder and Decoder0
Zero-resource Machine Translation by Multimodal Encoder-decoder Network with Multimedia Pivot0
Google's Multilingual Neural Machine Translation System: Enabling Zero-Shot TranslationCode0
Cross-lingual Dataless Classification for Languages with Small Wikipedia Presence0
Tricks from Deep Learning0
Increasing the throughput of machine translation systems using clouds0
Unsupervised Pretraining for Sequence to Sequence Learning0
The Neural Noisy Channel0
A Convolutional Encoder Model for Neural Machine TranslationCode0
Neural Machine Translation with ReconstructionCode0
Quasi-Recurrent Neural NetworksCode0
Show:102550
← PrevPage 153 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