Main Conference

Proceedings of AMTA 2016, vol. 1:  MT Researchers’ Track   Spence Green and Lane Schwartz (Eds.)

Proceedings of AMTA 2016, vol. 2:  MT Users’ Track   Olga Beregovaya, Jennifer Doyon, Lucie Langlois, and Steve Richardson (Eds.)

MT Marathons, Open Source, and Collaborative Research in MT   Phillip Koehn, Research Track Invited Talk



MT escaped from the Lab. Now what?   Mike Dillinger
Interactive Machine Translation: From Research to Practice Spence Green
DARPA Human Language Technology Programs   Doug Jones
Neural MT: Breaking the Performance Plateau Rico Sennrich



Dependency-based Statistical MT   Qun Liu & Liangyou Li

Computer Aided Translation: Advances and Challenges   Philipp Koehn

Advances in Neural Machine Translation   Rico Sennrich, Alexandra Birch, and Marcin Junczys-Dowmunt

ModernMT   Marcello Federico and Marco Trombetti



CAT Tool Workshop: Star Transit Presentation

AMTA 2016 is the twelfth biennial conference organized by the Association for Machine Translation in the Americas. The AMTA conferences are unique in bringing together MT researchers, developers, and users of MT technology from government and industry. This year’s AMTA will take place just before EMNLP 2016 in the same hotel, with a shared day of workshops.

Read more about this conference here!

Here is some of most prestigious international conferences and scientific journals that publish research papers related to machine translation. AMTA and MT Summit  are focused on machine translation, computer-aided human translation, and tools for human translators. They are both affiliated with our association and we very much encourage you submit your original research work their. However, there are other venues for publishing MT research.

The list below provides you with some of those venues:

International Conferences and Workshops:

Features of machine translation (MT) implementations and project efforts in official settings, regardless of jurisdiction, are guided by at least three attributes common to administration of authority.

Fact-based Decision-making

The first is the expectation of fact-based decision-making. Demands for MT in government settings are–due to state needs for information from unofficial sources in different languages–most often characterized as MT for assimilation. Yet, there also exist civil, defense and economic requirements to create precise versions of crucial source language (SL) documents, such as international agreements, treaties and legally binding certificates, in many varied target languages (TL).  These are government functions that motivate the development of MT for dissemination as well.

Market Drivers

The absence of a market driver is another factor.  In industry, companies and financial institutions may base their plans for MT resourcing on the bright, say manufacturing, prospects of a given country, whose language’s handling they want their MT technology investments to address.  By contrast, the interest of governance is served by global concerns of an orthogonal nature.  Whether they be defensive, political, medical or humanitarian, state responsibilities entail first the health and welfare of the populace.  Hence, government MT resourcing necessarily focuses on languages of the countries that may threaten that welfare.  Increasingly, in recent years, those countries host communities speaking languages of low diffusion, resources for which are scarce.

Scope and Simultaneous Demands

Lastly, the broad scope, the timely responses required, and the many, often simultaneous demands levied on government decision-makers conspire to create a singularly focused environment.  To process information in multiple languages under these conditions, MT must not only be equipped with specialized glossary, jargon and name recognition modules but also incorporated into workflows which handle text variety and volume at effective rates of speed, or velocities.  In other words, MT for government analysts must be adaptive, with specialized modules, as well as integrated into workflows of enabling technologies which address the conditions in which language and information analysts access it.  The domains, genres and medium-based registers in which institutions must operate, so as effectively to govern, combine in unpredictable ways to constitute, in effect, their own language varieties.  This unique fusion of diversity of language use, topic areas in its purview, and need for contemporaneous handling of several perspectives on many situations constitutes the third of the attributes affecting the resourcing of MT for Government Analysts.

Example Deployments and Initiatives

Cybertrans, Language Now, Systran Government Enterprise licenses, NMEC, NVTC approaches–those translating in regular dialogue with developers. Successful deployment of MT systems into government operations usually requires an avid proponent within the analyst community. This was the case with Cybertrans effort as well as the NMEC effort. Programs:  Army MFLTS, JUONS, MNSTC (Eng-Dari, Eng-Pashto) Research Initiatives:  DARPA MADCAT-K, DIA CACI MJ..-K BOLT, DEFT, Content Understanding, IARPA BABEL, Army MURI in the MT of Low Resource Languages [[CMU LTI, USC ISI, UT, MIT]]

Since machine translation started to be commercially available, commercial users of machine translation had the challenge to identify use cases where MT increases value for the respective company. Over the years, three major use case categories seem to have evolved:

Machine translation as a service can be either a byproduct for some teams and companies that develop MT technology for above mentioned use cases, or they focus on MT technology development, that customers then use for these use cases. The use cases in this category can also be from MT service, over HAMT service, to machine-aided human translation MAHT service.

MT as a service is offered in different business models:

  1. The oldest model is the machine-based perpetual software license (MBPSL). This model allows the user to use the machine translation service (most of the time on hardware the user has to purchase separately) from the time the license is purchased. Maintenance contracts allow the user to receive updates and enhancements timely and either for free or for a discounted price.
  2. The second model is the machine-based annual software license (MBASL). This model allows the user to purchase a license similar to the machine-based perpetual license, but the license is constrained to only one year, and has to be renewed or extended annually. The advantage of this is that the upfront cost is lower, the disadvantage is that the the total cost is usually higher than MBPSL plus maintenance, if the user decides to stay in the same licensing model.
  3. The third model is the volume-based service usage pricing (VBSUP). This is a service, where a translation service is offered, and the pricing is by word, by character, by byte or another unit. Other dimension is often to allow the user to pick and choose the expected quality, e.g. by allowing different levels where the human is in the loop, or by using more hardware resources for each translation (and higher cost at the provider’s side, therefor the higher cost to the consumer).

Google Translate

Google Translate is a translation service that provides instant translations between dozens of different languages. It can translate words, sentences and web pages between any combination of our supported languages. With Google Translate, we hope to make information universally accessible and useful, regardless of the language in which it’s written. When Google Translate generates a translation, it looks for patterns in hundreds of millions of documents to help decide on the best translation for you. By detecting patterns in documents that have already been translated by human translators, Google Translate can make intelligent guesses as to what an appropriate translation should be. This process of seeking patterns in large amounts of text is called “statistical machine translation”. Since the translations are generated by machines, not all translation will be perfect. The more human-translated documents that Google Translate can analyse in a specific language, the better the translation quality will be. This is why translation accuracy will sometimes vary across languages.

Microsoft Translator

Bing Translator (previously Live Search Translator and Windows Live Translator) is a user facing translation portal provided by Microsoft as part of its Bing services to translate texts or entire web pages into different languages. All translation pairs are powered by the Microsoft Translator statistical machine translation platform and web service, developed by Microsoft Research, as its backend translation software. Two transliteration pairs (between Chinese Traditional and Chinese Simplified) are provided by Microsoft’s Windows International team.

SDL BeGlobal

With SDL BeGlobal, business users are now enabled to manage secure, global and trusted communications with customers in real-time through one central interface for multiple types of content, communication and social media while significantly reducing their translation costs. The application can also be used by translation teams to increase productivity for content that requires human translation or review or reduce post-editing costs through crowd-sourcing.


SYSTRAN’s SYSTRANLinks is a comprehensive website-translation solution, it offers an online CMS platform that lets you launch and manage your localization projects with unprecedented ease – all from an intuitive centralized base. And it gives you a rich range of user-friendly tools that allow you to constantly enhance your content and manage the entire localization process more easily.


IBM® WebSphere® Translation Server for Multiplatforms is a machine translation (MT) offering that can help companies remove language as a barrier to global communication and commerce. It allows you to leverage your existing web infrastructure to provide content to users in their native language at a lower cost than traditional translation.

WebSphere Translation Server for Multiplatforms:

– Provides a robust, scalable platform for providing content in multiple languages.

– Offers advanced MT features to accelerate translation, lower costs and help improve customer service.

– Integrates with your existing web infrastructure to help simplify and lower the costs of integration and implementation efforts.

Since machine translation started to be commercially available, commercial users of machine translation had the challenge to identify use cases where MT increases value for the respective company. Over the years, three major use case categories seem to have evolved:

For the category of workflow optimization, the main criterion is “cost”, but also “revenue”. To achieve that, MT use is put in the different workflows to minimize human involvement and therefore cost, or to increase speed of translation and therefore generating a competitive advantage. In some cases, the use of own technology is preferred, either in-house development, building on top of open source technology, or by using third-party MT tools. The use cases in this category can be from a fully automated translation service (MT service), over human-aided machine translation (HAMT service), to machine-aided human translation (MAHT service).
Adobe – case study
Adobe now uses Machine Translation plus post-editing as the default localization process for all of its product documentation and most of its UI.  The MT engines are customized using in-house translation memories, and post-editing is charged at a discounted rate as compared to translation from scratch.  The discounts are set by calculating the amount of time saved by post-editing.
TransPerfect – case study
TransPerfect’s proprietary methodology combines machine translation with complementary technologies and human translators to quickly and reliably produce usable translations for review of large volumes of text, all completed in a fraction of the time that would be required for a standard translation process. While machine translation quality falls far short of human translation, if used properly in conjunction with human reviewers, the utility of machine translation can be stretched to include both non-distribution applications including document review, legal discovery, and internal correspondence, as well as distribution-level materials for which extremely fast turnaround times are a requirement.
Etsy – case study
Etsy, an e-commerce marketplace specializing in vintage, art, and handmade goods, recently released a test integration of Machine Translation on user product listing.  Listings in a small set of non-English languages are automatically translated into English, allowing those sellers access to a much wider audience of buyers.  The hypothesis guiding the test is that although commercial transactions is an area where extremely high translation quality is traditionally required, the Machine Translation can provide enough understanding that users feel confident to complete the transaction.

AMTA 2018 | Proceedings for the Conference, Keynotes, Workshops and Tutorials

by Mike Dillinger | March 21, 2018

Main Conference Research Track Download (2.7 MB) Commercial and Government Tracks Download (28.4 MB)   Keynotes Arianna Bisazza – Leiden University Research Keynote | Unveiling the Linguistic Weaknesses of Neural MT Download (4 MB) Macduff Hughes – Google Commercial Keynote | Machine Translation Beyond the Sentence Download (2.7 MB) Carl Rubino – IARPA Government Keynote […]

AMTA 2018

AMTA 2018 | Tutorial | Getting Started Customizing MT with Microsoft Translator Hub: From Pilot Project to Production

by Mike Dillinger | January 30, 2018

Develop an Effective MT Customization Pilot Project Learn strategies to plan and carry out an effective pilot project to train a customized MT engine and learn tips to evaluate the MT pilot project against your goals so you can move it toward production. Participants will know how to plan a pilot project, select appropriate training […]

AMTA 2018

AMTA 2018 | Workshop | The Role of Authoritative Standards in the MT Environment

by Mike Dillinger | January 30, 2018

In this workshop, we will bring together experts from across the standards community, including from the American Society for Testing and Materials (now just “ASTM International”), the American National Standards Institute (ANSI), the International Organization for Standardization (ISO), the Globalization and Localization Association (GALA), and the World Wide Web Consortium (W3C). These experts will discuss authoritative standards that […]

AMTA 2018

AMTA 2018 | Tutorial | ModernMT: Open-Source Adaptive Neural MT for Enterprises and Translators

by Mike Dillinger | January 30, 2018

Nowadays, computer-assisted translation (CAT) tools represent the dominant technology in the translation market – and those including machine translation (MT) engines are on the increase. In this new scenario, where MT and post-editing are becoming the standard portfolio for professional translators, it is of the utmost importance that MT systems are specifically tailored to translators. […]

AMTA 2018

AMTA 2018 | Tutorial | MQM-DQF: A Good Marriage (Translation Quality for the 21st Century)

by Mike Dillinger | January 30, 2018

In the past three years, the language industry has been converging on the use of the MQM-DQF framework for analytic quality evaluation. It emerged from two separate quality-evaluation approaches: the European Commission-funded Multidimensional Quality Metrics (MQM) and the Dynamic Quality Framework (DQF) from TAUS. Harmonized in 2015, the resulting shared hierarchy of error types allows […]

AMTA 2018

AMTA 2018 | Tutorial | A Deep Learning curve for Post-Editing

by Mike Dillinger | January 30, 2018

Does post-editing also require a deep learning curve? How do the neural networks of post-editors work in concert with neural MT engines? Can post-editors and engines be retrained to work more effectively with each other? In this tutorial, we demystify the process, focus on the latest MT developments and their impact on post-editing practices. We […]

AMTA 2018