Is Neural Machine Translation Ready for Deployment? A Case Study on 30 Translation Directions

In this paper we provide the largest published comparison of translation quality for phrase-based SMT and neural machine translation across 30 translation directions. For ten directions we also include hierarchical phrase-based MT. Experiments are performed for the recently published United Nations Parallel Corpus v1.0 and its large six-way sentence-aligned subcorpus. In the second part of the paper we investigate aspects of translation speed, introducing AmuNMT, our efficient neural machine translation decoder. We demonstrate that current neural machine translation could already be used for in-production systems when comparing words-persecond ratios.

• Publication year

  2016

• Venue

  International Workshop on Spoken Language Translation

• Publication date

  2016-10-04

• Fields of study

  Linguistics, Computer Science

• Identifiers
  arXiv 1610.01108
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Log-linear Combinations of Monolingual and Bilingual Neural Machine Translation Models for Automatic Post-Editing

  2016cited by this paper
• The AMU-UEDIN Submission to the WMT16 News Translation Task: Attention-based NMT Models as Feature Functions in Phrase-based SMT

  2016cited by this paper
• The United Nations Parallel Corpus v1.0

  2016cited by this paper
• Vocabulary Manipulation for Neural Machine Translation

  2016cited by this paper
• Neural Interactive Translation Prediction

  2016cited by this paper
• Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation

  2016cited by this paper
• Edinburgh Neural Machine Translation Systems for WMT 16

  2016cited by this paper
• Neural Machine Translation of Rare Words with Subword Units

  2015cited by this paper
• Neural Machine Translation by Jointly Learning to Align and Translate

  2014cited by this paper
• Addressing the Rare Word Problem in Neural Machine Translation

  2014cited by this paper
• On Using Very Large Target Vocabulary for Neural Machine Translation

  2014cited by this paper
• Large-scale Multiple Language Translation Accelerator at the United Nations

  2013cited by this paper
• Scalable Modified Kneser-Ney Language Model Estimation

  2013cited by this paper
• Can Markov Models Over Minimal Translation Units Help Phrase-Based SMT?

  2013cited by this paper
• Efficient Estimation of Word Representations in Vector Space

  2013cited by this paper
• Phrasal Rank-Encoding: Exploiting Phrase Redundancy and Translational Relations for Phrase Table Compression

  2012cited by this paper
• ADADELTA: An Adaptive Learning Rate Method

  2012cited by this paper
• On the difficulty of training recurrent neural networks

  2012cited by this paper
• Parallel Implementations of Word Alignment Tool

  2008cited by this paper
• Improving Translation Quality by Discarding Most of the Phrasetable

  2007cited by this paper
• Moses: Open Source Toolkit for Statistical Machine Translation

  2007cited by this paper

• Assessing the Impact of Typological Features on Multilingual Machine Translation in the Age of Large Language Models

  2026cites this paper
• Instability in Downstream Task Performance During LLM Pretraining

  2025cites this paper
• MedBot: A Novel Sequential Pipeline for Context Recognition Based on SciSpacy and Med7 Entity Recognizer

  2024cites this paper
• Esposito: An English-Persian Scientific Parallel Corpus for Machine Translation

  2024cites this paper
• Optimized English Translation System Using Multi-Level Semantic Extraction and Text Matching

  2024cites this paper
• College Translation Teaching in the Era of Artificial Intelligence: Challenges and Solutions

  2024cites this paper
• Low Resource Arabic Dialects Transformer Neural Machine Translation Improvement through Incremental Transfer of Shared Linguistic Features

  2024cites this paper
• Tasaheel-v2: Development of Innovative Textual Analysis tool with Advanced Features

  2024cites this paper
• Machine translation literacy in the legal translation context: a SWOT analysis perspective

  2024cites this paper
• Übersetzen im Wandel

  2024cites this paper
• Research on Key Technologies of Neural Machine Translation Based on Deep Learning

  2024cites this paper
• The Impact of Multilinguality and Tokenization on Statistical Machine Translation

  2024cites this paper
• Text Prompt Translation for Zero Shot Prediction under Lexical Constraint in Aviation Domain

  2023cites this paper
• An Improved LA-Transformer Machine Translation Model

  2023cites this paper
• Translating Braille into Chinese based on improved CBHG model

  2023cites this paper
• Opportunities and Implementation of Neural Machine Translation for Network Configuration

  2023cites this paper
• On the Evaluation of Terminology Translation Errors in NMT and PB-SMT in the Legal Domain: a Study on the Translation of Arabic Legal Documents into English and French

  2023cites this paper
• Linguistically-Motivated Yorùbá-English Machine Translation

  2022cites this paper
• On the Use of Morpho-Syntactic Description Tags in Neural Machine Translation with Small and Large Training Corpora

  2022cites this paper
• Revisiting Checkpoint Averaging for Neural Machine Translation

  2022cites this paper
• Patents and knowledge diffusion

  2022cites this paper
• A Method of Chinese-Vietnamese Bilingual Corpus Construction for Machine Translation

  2022cites this paper
• Floating-gate based PN blending optoelectronic synaptic transistor for neural machine translation

  2022cites this paper
• Out of the BLEU: An Error Analysis of Statistical and Neural Machine Translation of WikiHow Articles from English into Arabic

  2021cites this paper
• AraT5: Text-to-Text Transformers for Arabic Language Understanding and Generation

  2021cites this paper
• RoFormer: Enhanced Transformer with Rotary Position Embedding

  2021cites this paper
• Improving Data Augmentation for Low-Resource NMT Guided by POS-Tagging and Paraphrase Embedding

  2021cites this paper
• Comparing NMT and PBSMT for post-editing in-domain formal texts: A case study

  2021cites this paper
• Data augmentation for low‐resource languages NMT guided by constrained sampling

  2021cites this paper
• Investigating usability in postediting neural machine translation: Evidence from translation trainees' self-perception and performance

  2021cites this paper
• AraT5: Text-to-Text Transformers for Arabic Language Generation

  2021cites this paper
• Gender Bias in Neural Machine Translation

  2021cites this paper
• What do post-editors correct? A fine-grained analysis of SMT and NMT errors

  2021cites this paper
• Translating the Unseen? Yorùbá → English MT in Low-Resource, Morphologically-Unmarked Settings

  2021cites this paper
• Chinese Medical Paraphrase Generation: Based on Neural Machine Translation

  2021cites this paper
• Analisis Perbandingan Nilai Akurasi Mekanisme Attention Bahdanau dan Luong pada Neural Machine Translation Bahasa Indonesia ke Bahasa Melayu Ketapang dengan Arsitektur Recurrent Neural Network

  2021cites this paper
• Efficient English Translation Method and Analysis Based on the Hybrid Neural Network

  2021cites this paper
• Incorporating translation quality estimation into Chinese-Korean neural machine translation

  2021cites this paper
• First the Worst: Finding Better Gender Translations During Beam Search

  2021cites this paper
• Neural Machine Translation: A Review of Methods, Resources, and Tools

  2020cites this paper
• Neural machine translation of low-resource languages using SMT phrase pair injection

  2020cites this paper
• A Tale of Eight Countries or the EU Council Presidency Translator in Retrospect

  2020cites this paper
• Language Technology Platform for Public Administration

  2020cites this paper
• Machine Translation Quality: A comparative evaluation of SMT, NMT and tailored-NMT outputs

  2020cites this paper
• EXTENDED CONVOLUTIONAL NEURAL NETWORKS POST-TRAINED WITH FACTORED STATISTICAL MACHINE

  2020cites this paper
• The Roles of Language Models and Hierarchical Models in Neural Sequence-to-Sequence Prediction

  2020cites this paper
• UPC: An Open Word-Sense Annotated Parallel Corpora for Machine Translation Study

  2020cites this paper
• Machine Translation Using Improved Attention-based Transformer with Hybrid Input

  2020cites this paper
• Deep Neural Network--based Machine Translation System Combination

  2020cites this paper
• The Sockeye 2 Neural Machine Translation Toolkit at AMTA 2020

  2020cites this paper
• Korean-Vietnamese Neural Machine Translation with Named Entity Recognition and Part-of-Speech Tags

  2020cites this paper
• R EPRESENTATION AND B IAS IN M ULTILINGUAL NLP: I NSIGHTS FROM C ONTROLLED E XPERIMENTS ON C ONDITIONAL L ANGUAGE M ODELING

  2020influential citation
• A Survey of Deep Learning Techniques for Neural Machine Translation

  2020cites this paper
• Neural Machine Translation

  2020cites this paper
• Sprachvarietäten- abhängige Terminologie in der neuronalen maschinellen Übersetzung: Eine Analyse in der Sprachrichtung Englisch-Deutsch mit Schwerpunkt auf der österreichischen Varietät der deutschen Sprache

  2020influential citation
• Quantitative Analysis of Post-Editing Effort Indicators for NMT

  2020cites this paper
• Analysing terminology translation errors in statistical and neural machine translation

  2020cites this paper
• Transforming machine translation: a deep learning system reaches news translation quality comparable to human professionals

  2020cites this paper
• Neural machine translation: Challenges, progress and future

  2020cites this paper
• An Error-based Investigation of Statistical and Neural Machine Translation Performance on Hindi-to-Tamil and English-to-Tamil

  2020cites this paper
• Comparing Statistical and Neural Machine Translation Performance on Hindi-To-Tamil and English-To-Tamil

  2020cites this paper
• Approximating neural machine translation for efficiency

  2020cites this paper
• Take Help from Elder Brother: Old to Modern English NMT with Phrase Pair Feedback

  2019cites this paper
• A product and process analysis of post-editor corrections on neural, statistical and rule-based machine translation output

  2019cites this paper
• Consistency by Agreement in Zero-Shot Neural Machine Translation

  2019cites this paper
• Post-editing neural machine translation versus phrase-based machine translation for English–Chinese

  2019cites this paper
• CUED@WMT19:EWC&LMs

  2019cites this paper
• Translating with Bilingual Topic Knowledge for Neural Machine Translation

  2019cites this paper
• TermEval: an automatic metric for evaluating terminology translation in MT

  2019cites this paper
• Improved Arabic-Chinese Machine Translation with Linguistic Input Features

  2019cites this paper
• Context in Neural Machine Translation: A Review of Models and Evaluations

  2019influential citation
• Attention With Sparsity Regularization for Neural Machine Translation and Summarization

  2019cites this paper
• An in-depth Study of Neural Machine Translation Performance

  2019cites this paper
• Attention Mechanism in Machine Translation

  2019cites this paper
• SubCharacter Chinese-English Neural Machine Translation with Wubi encoding

  2019cites this paper
• Exploring Machine Translation on the Chinese-Vietnamese Language Pair (Extended Abstract)

  2019cites this paper
• Arabic–Chinese Neural Machine Translation: Romanized Arabic as Subword Unit for Arabic-sourced Translation

  2019cites this paper
• Statistical-based system combination approach to gain advantages over different machine translation systems

  2019cites this paper
• Post-editing Productivity with Neural Machine Translation: An Empirical Assessment of Speed and Quality in the Banking and Finance Domain

  2019cites this paper
• Neural Machine Translation: A Review

  2019cites this paper
• A Comparison of Data-Driven and Template-Based Approaches to Natural Language Generation

  2019cites this paper
• How does the post-editing of Neural Machine Translation compare with from-scratch translation? A product and process study

  2019cites this paper
• Does NMT make a difference when post-editing closely related languages? The case of Spanish-Catalan

  2019cites this paper
• Statistical versus neural machine translation – a case study for a medium size domain-specific bilingual corpus

  2019cites this paper
• Hybrid Machine Translation by Combining Output from Multiple Machine Translation Systems

  2019cites this paper
• When a ‘sport’ is a person and other issues for NMT of novels

  2019cites this paper
• Taking MT Evaluation Metrics to Extremes: Beyond Correlation with Human Judgments

  2019cites this paper
• The CUED’s Grammatical Error Correction Systems for BEA-2019

  2019influential citation
• Multi-Round Transfer Learning for Low-Resource NMT Using Multiple High-Resource Languages

  2019cites this paper
• Comparative Quality Estimation for Machine Translation. An Application of Artificial Intelligence on Language Technology using Machine Learning of Human Preferences

  2019cites this paper
• Terminology Translation in Low-Resource Scenarios

  2019cites this paper
• What Level of Quality can Neural Machine Translation Attain on Literary Text?

  2018cites this paper
• Approaching Neural Grammatical Error Correction as a Low-Resource Machine Translation Task

  2018cites this paper
• Exploring Hyper-Parameter Optimization for Neural Machine Translation on GPU Architectures

  2018influential citation
• Training and Adapting Multilingual NMT for Less-resourced and Morphologically Rich Languages

  2018influential citation
• Exploiting Pre-Ordering for Neural Machine Translation

  2018cites this paper
• Investigating Backtranslation in Neural Machine Translation

  2018cites this paper
• Tilde MT Platform for Developing Client Specific MT Solutions

  2018cites this paper
• Neural versus phrase-based MT quality: An in-depth analysis on English-German and English-French

  2018cites this paper
• Machine Translation Systems for WMT 2017

  2018influential citation