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.
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.
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.
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:
- 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.
- 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.
- 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.
http://googletranslate.blogspot.com
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.
http://blogs.msdn.com/b/translation/
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.
http://www.sdl.com/products/sdl-beglobal/
SYSTRAN
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.
http://blog.systranlinks.com
IBM
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.
http://www.ibm.com/software/products/en/translation-server
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.
http://blogs.adobe.com/globalization/more-content-into-more-languages/
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.
https://www.transperfect.com/services/translation_machine.html
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.
https://blog.etsy.com/news/2013/translating-the-marketplace-in-more-ways-than-one/
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:
The category of use cases that try to cope with the “big data” challenge is mainly trying to make large data available to more potential consumers of these data. The criteria on whether MT helps or not is directly derived by the behavior of the millions of users if interacted with content that was translated. But in any case, the financial impact is measured finally in “revenue”.
Google – case study
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.
http://googletranslate.blogspot.com
eBay – case study
eBay has developed its very own machine translation tools to help fuel expansion in Russia. The tools allow Russian buyers to get accurate translations of eBay seller listing and communications in real time, making working with eBay much easier for international transactions. In 2013, eBay began to use machine translation in the eBay environment to enable people across country boundaries to communicate and deal with each other. eBay rolled out their first machine translation technology in January, translating Russian to/from English in real-time. Machine translation is used to match user queries and products in the inventory across languages (query translation), and to present the results to the user translated into the language of the user’s original query. This opens up new avenues for sellers around the world to reach global buyers, across language barriers. Currently, eBay translates millions of queries and query results daily per language.
http://blog.ebay.com/machine-translation-at-ebay/
Microsoft – case study
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.
http://blogs.msdn.com/b/translation/
Facebook – case study
Facebook’s latest acquisition could help it connect users across language barriers. It has just announced that it’s acquired the team and technology of Pittsburgh’s Mobile Technologies, a speech recognition and machine translation startup that developed the app Jibbigo. From voice search to translated News Feed posts, Facebook could to a lot with this technology.
Facebook tells me “We’ll continue to support the [Jibbigo] app for the time being.” Jibbigo launched in 2009, and allows you to select from over 25 languages, record a voice snippet in that language or type in some text, and then get a translation displayed on screen and read aloud to you in a language of your choosing.
http://jibbigo.com/index.html
Some References and Reads:
Machine Translation and Professional Translators Community
During the last couple of years, machine translation post-editing has become one of the hottest most discussed topics in the translation industry as evidenced by conferences, forums and webinars. What is the motivation driving this new found interest?
Translators are motivated to use machine translation output since the quality of engines has reached the point where using them leads to proven productivity gains, ranging between 30 and 300%. Thus, machine translation is becoming a commonplace productivity tool similar to translation memories. The emergence of several post-editing standards that are tied to the desired quality levels of the final output allows translators to have additional income opportunities translating content that previously remained monolingual.
Machine translation is still not perfect, and there are recurring challenging issues for post-editors such as lexical coverage, word order, compound formation, word form agreement, omissions and several more. However, a recent positive development, established feedback loops back to the MT engine developers and deployment managers, gives translators more confidence in future engine improvements.
Just as with human translation, post-editing throughput can vary and depends on:
- language pair
- content type & complexity
- experience
- domain knowledge
- quality requirements
- use of automatic QA tools
- quality of training data and reference material
AMTA is actively supporting machine translation as a productivity tool both for language service providers and freelance translators. In all of our past conferences, members of the professional translation community presented their findings on MT adoption as a part of the commercial user track (URL to the past conference proceedings). Synchronizing AMTA and ATA (American Translators Association) conferences for several years helped both organizations drive attendance and draw interest to the topic of machine translation as a productivity tool for translators.
Training professional post-editors
What is post-editing?
The “term used for the correction of machine translation output by human linguists/editors” (Veale and Way 1997)
“Checking, proof-reading and revising translations carried out by any kind of translating automaton”. (Gouadec 2007)
The choice of whether to translate from scratch (“human translation”) or post-edit machine-translated output is driven by the suitability of the source content for machine translation. <>To-date the professional translators community has reported to be achieving the best results with post-editing the more formal, organized and structured content types with repetitive syntactic patters and predictable use of terminology, which makes them easier for the machine translation engines to handle:
• Contracts
• Patents
• Annual Corporate Reports
• Light Marketing (as opposed to “transcreation”)
• Software Documentation
• Software User Interface
• SEO (Search Engine Optimization) keywords
• e-Learning Content
• User Guides and Product Manuals
• Internal Corporate Communications
• Wikis
• Knowledge Bases
• Proposals / Draft Applications
The decision on which post-editing quality level to select is mainly determined by the visibility, perishability and the target audience for the content, or “utility”, which is the term lately adopted by the industry. The content utility also dictates the number of errors and the error type tolerance for the given content type. As outlined in the TAUS post-editing guidelines, it is essential that the post-editors are given very explicit and clear set of instructions that describe the desired quality levels.
At the moment two levels of post-editing are recognized as industry standard: “good enough”, often referred to as “light post-editing”, and “publishable”, where the final output quality is expected to be on par with the translation performed from scratch.
The table below is an example of two levels of post editing:
The best results are achieved when post editors and machine translation engine developers are in a continuos constructive dialog around the challenges translators are facing when post editing the MT output. This both allows the post-editors to build the sense of ownership of the engines, and helps the developers to tailor their engine roadmap to the actual needs of translators.
While the “adequacy” – related feedback helps with selecting the appropriate engine training data, the “fluency” and “readability” feedback helps with fine-tuning the core engine functionality, including the language-related and the engineering issues, such as handling of metadata and locale-specific conventions.
Recognizing the need for developing a skilled and qualified post-editors workforce, several major Language Service Providers and now publish their “how-to” introductory courses on the principles and best practices for post-editing machine translation output:
Welocalize: http://www.welocalize.com/wemt/machine-translation-overview/
SDL: http://www.sdl.com/campaign/lt/eBooks/language-technology-ebooks-tab2.html#tabs
Hunnect: http://www.hunnectacademy.com/en/content/content/7
Industry Initiatives on Post-editing Machine Translation Output
Below are URLs to some of the industry initiatives relevant to the use of machine translation as a post-editing productivity tool. The list in maintained in a “work in progress” mode and is being updated regularly.
TAUS Post-Editing Guidelines (created in partnership with CNGL): general post-editing guidelines for “good enough” and “human translation level” post-editing. TAUS has also recently published guidelines on pricing post-editing work and measuring post-editors’ productivity.
TAUS Dynamic Quality Framework: a set of tools and methodologies for evaluating post-editors’ productivity, selecting a machine translation engine most suitable for a specific project and reviewing machine translation and post-editing errors in a structured environment.
QTLaunchpad: European Commission-funded collaborative research initiative dedicated to overcoming quality barriers in machine and human translation and language technologies.
2013 MT Summit Workshop on Post-Editing Technologies and Practice: a recent workshop on post-editing organized by Dr. Sharon O’Brien, Michel Simard and Lucia Specia (follow the URLs to their professional web pages to see more publications).
There are several LinkedIn groups dedicated to post-editing of machine translation output and other translation automation tools:
Automated Language Translation (MT/Machine Translation): the group focusing on discussions around the trends and developments in machine translation, with the members both from the development and user side.
Hotel registration is open!
The AMTA 2016 Conference Hotel is the same as the conference venue:
The Austin Hilton Hotel
You can reserve your hotel room at the discounted conference rate here.
Reserve your rooms soon!
You can see the hotel on a map here. And a map of nearby restaurants is here.
Austin, TX is the Live Music Capital of the World!
You can find more about Austin here. And more about music in Austin here.
by Darius Hughes | October 7, 2016
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.
Users Read more...
by Darius Hughes | October 7, 2016
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
Users Read more...
by Darius Hughes | October 7, 2016
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
Users Read more...
by Darius Hughes | October 7, 2016
The category of use cases that try to cope with the “big data” challenge is mainly trying to make large data available to more potential consumers of these data.
Users Read more...
by Darius Hughes | October 7, 2016
During the last couple of years, machine translation post-editing has become one of the hottest most discussed topics in the translation industry as evidenced by conferences, forums and webinars.
Users Read more...
by Darius Hughes | August 5, 2016
Hotel registration is open! The AMTA 2016 Conference Hotel is the same as the conference venue: The Austin Hilton Hotel You can reserve your hotel room at the discounted conference rate here. Reserve your rooms soon! You can see the hotel on a map here. And a map of nearby restaurants is here. Austin, TX […]
Archieve Read more...
