A Trip down Memory Lane: KantanMT in 2015

KantanMT Year in ReviewWhile chatting over a mouthful of mince pies, some tourtière and a few classy glasses of mulled wine this week, we at KantanMT were suddenly struck by the realisation that 2015 was perhaps one of the most sensational, successful and eventful years for us in the company! And the fact is, we can’t wait to start working on everything that we have planned for 2016 – we are certain that the new year is going to be even more exciting for us.

Continue reading

What’s New in eCommerce in 2016? More Localization and Better Machine Translation

ECommerce_Whitepaper_KantanMT Download

If the post-Black Friday sales numbers are anything to go by, there’s no question any more that the face of eCommerce is changing, and with it, the brick-and-mortar retailers have started rethinking their business strategy. As this news piece about Scotland experiencing a major dip in shoppers goes on to prove, demand for online shopping will increase substantially in 2016. This in turn means that the need for content localization and translation for eTailers (online retailers) will be even more pressing during the coming new year. As the often quoted Common Sense Advisory report points out, 72.4% of consumers are more likely to buy from a site, which is in their native language.  Indeed, localization is no longer a good-to-have feature – it is now a must-have for all eCommerce businesses that aim to sell their products globally.

Chris Bishop, Managing Director of Microsoft Research, Cambridge, UK points out that “by 2026 we will have ubiquitous, human-quality translation among all European languages, thereby eliminating the language barrier throughout Europe.” Bishop’s prediction does not sound far off the mark at all when we take into account the fact that in the past ten years, Machine Translation (MT) has improved by leaps and bounds. Early MT was rules-based (RBMT) and required sets of linguistic rules, and it worked moderately well within a prescribed domain. However, this was resource intensive and cost prohibitive for many.

By 2026 we will have ubiquitous, human-quality translation among all European languages, thereby eliminating the language barrier throughout Europe

Chris Bishop, Managing Director of Microsoft Research, Cambridge, UK

The turning point for using MT in business came with the advent of the Internet, the SaaS model and the open source development model for software. These new changes in technology helped build the foundation for Statistical Machine Translation (SMT) research, and subsequently the open source development of the Moses Decoder. Moses enabled researchers and private companies to commercialise Statistical MT and develop it to the custom solutions it is today. The year of 2016 and beyond, will see further research in the fields of Natural Language Processing (NPL), Deep learning and machine learning, contributing directly to immense improvements in the fields of Custom MT.

The KantanMT Business Team published a new white paper, which provides an in depth understanding of how eTailers in 2016 will be affected by Machine Translation, and also goes on to discuss how Custom Machine Translation when compared to generic MT systems, will emerge as the clear winner in solving eTailing localization issues in the coming year.

Here are some of the highlights how MT will evolve in 2016 for eTailers:

  • eTailers will use a combination of only CMT or CMT and Human Post-Editing to reach new markets ahead of their competitors
  • With increased multilingual customer demand for products, content translation will find support in auto scaling
  • Custom Machine Translation will be used more widely as eCommerce customers expand globally

download_call

Summary:

Machine Translation is no longer a luxury. It is an essential component as a Tier 1 application to support global business. The purpose of this paper is to highlight how Machine Translation and more importantly Custom Machine Translation technology has come of age, in terms of quality, speed and scalability. During 2016 and beyond eTailers need to ensure that they review their globalization strategies to reflect these advances in technology, so they can maximise their global growth potential.

Download the KananMT white paper on eCommerce today!

eComm_whitepaper_calltoaction

Intelligent Content Distribution is Important – But How Intelligently are you Producing Your Content?

The future of content production, distribution and consumption is here. With the number of websites at 949,891,800 as of the time of publication of this blog, and increasing every second, the importance of developing structured content and its distribution has become more important than eArtificial Intelver. It is no coincidence that in the 2015 tcworld Conference held in Stuttgart, Germany, one of the main themes of discussion is Intelligent Information management.

The speakers will present on the “megatrend of our time” where content needs to cater to “smart” users through “smart” services and not “just” products. As a result of this new trend, companies need to step up to the challenge and provide users with individualised information at the right time, in the right place and in the medium of their choice. Tekom calls this the “Intelligent Information Initiative – in3.” Before talking a bit more about what Intelligent Content is all about, it is important to remember that while the structure of the content is incredibly important, it is also equally important to have content that’s relevant, reusable and above all, targeted to the “smart” users that companies aim to attract.

To know more about the speakers for this theme and the topics being presented, have a look at the tcworld conference schedule.

What’s Intelligent Content?

So what is intelligent content, and how can businesses effectively manage their content to get their products and services to market faster, without having to create new content for each new platform or medium.

Intelligent content adopts digital texts and multimedia with coding. This allows the coded content to be automatically processed for being accessed across various devises and interface.

The Intelligent bit is created by removing the formatting and adding metadata, which summarises the information related to the data. This makes finding and reusing the data/ content much easier. The metadata adds information to segments of the content, which in turn makes the content easy to be disseminated, discovered and reused by businesses.

Ann Rockley of the Rockley group fame has spoken in depth about Intelligent Content development in her work Managing Enterprise Content and she describes the importance of adopting the structure of intelligent content as follows:

Intelligent content enables automated multi-channel delivery, adaptive content, improved content discovery, and personalized content delivery in an agile world. But the power of your content to respond to tight timelines, new customer requirements, and increasing costs is based on the quality of your intelligent content strategy

It is this “quality” of content strategy that will either make you a leader in your industry or slow you down from being able to be the first to bring your product to market. If you are taking your “smart” services and products to users across the globe, or even starting your content strategy from scratch, it is important that you structure your content. This will not only make it easy to reuse and tag, but will also be extremely helpful for you when you have to get your content localized and translated into the languages of the markets you want to penetrate.

Structured content is incredibly suited to Machine Translation. And a quality (intelligent) content strategy should always plan ahead for the need of localization in the future. Even if your business is just starting off, you should begin planning your content strategy intelligently because an unstructured website can escalate into an unmanageable mess very quickly.

The real success of a company’s content strategy is knowing how and where it is consumed. Luckily the ‘always on’ availability of content means anyone can access information regardless of nationality and geographical location. If a company is serious about its content strategy, then it will put a process in place to create multilingual content that can be distributed to a multilingual audience.

Including Machine Translation into your Translation and localization Workflow will make it easier to translate more content, faster than traditional human only workflows. When your MT engine is integrated into your content management workflow, translations for your structured content can be sent to your global websites seamlessly, with minimal manual intervention.

Thanks to high success rates KantanMT has working with Structured Content, we believe that integrating Machine Translation into the workflow and planning an “quality” Intelligent Content Strategy go hand in hand.

Meet us at booth 2/A09 during the tekom trade fair and tcworld conference between 10th aTc Worldbd 12th November to learn more about Custom Machine Translation and how it can fit in your intelligent content production workflow.

We have a few  FREE Tekom Fair tickets to give away, so to be in with a chance to win, send an email to marketing@kantanmt.comwith ‘FREE Ticket’ in the subject line and we will add you to a draw. Winners will be notified by email.

Improving workflow integration and efficiency with KantanAPI

What is the KantanAPI?

KantanAPI enables KantanMT clients to interact with KantanMT as an on-demand web service. It also provides a number of different services including translation, file upload and retrieval and job launches.

With the KantanAPI  you not only have the opportunity to integrate KantanMT into your workflow systems but also the ability to receive on-demand translations from your KantanMT engines. All these services make the experience with Machine Translation as seamless as possible.

Accessing KantanAPI

Please Note: The API is only available to KantanMT members in the Enterprise Plan.

To access the KantanMT API you will first need your ‘API token’. This token can be found in the ‘API’ tab on the ‘My Client Profiles’ page of your KantanMT account.

Once you have your token you can use the API in a number of ways

  1. Using the API tab on the ‘My Client Profiles’ page in the KantanMT Web interface
  2. Using the REST interface via HTTP GET or POST requests
  3. Using one of our various connectors, which are built using our KantanAPI

For more details on implementing your API solution via the REST interface, please see the full API technical documentation at the following link:

How to use KantanAPI?

Login into your KantanMT account using your email and your password.

You will be directed to the ‘My Client Profiles’ page. You will be in the ‘Client Profiles’ section of the ‘My Client Profiles’ page. The last profile you were working on will be ‘Active’.

If you wish to use the ‘KantanAPI’ with another profile other than the ‘Active’ profile. Click on the profile you wish to use the ‘KantanAPI’ with, then click on the ‘API’ tab.

API tab

You will be directed to the ‘API Settings’ page. Now click on the ‘Launch API’ button.

Launching API

A ‘Launch API’ pop-up will now appear on your screen asking you ‘Are you sure you want to launch the API?’ Click ‘OK’.

launch Pop-up alert

The ‘API Status’ will now change from ‘offline’ to ‘initialising’, the ‘Launch API’ button will now change to ‘Launching API’ .

Launching API

When your KantanAPI launches the ‘API Status’ will now change from ‘initialising’ to ‘running’, the ‘Launching API’ button changes to ‘Shutdown API’ and you should now be able to click on the ‘Translate’ button.

API running

Type the text you wish to translate in the text box and click on the ‘Translate’ button.

Translating

The translated text will now appear in the ‘Translated Text’ box. If you wish to make any changes to the translated text simply place the cursor inside the ‘Translated Text’ box and make the changes. Save these changes by clicking the ‘Retrain Engine’ button.

Retrain Engine

Test if your engine was successfully retrained by clicking the ‘Translate’ button. The retrained text will now appear in the ‘Translated Text’ box.

If you don’t wish to retrain your engine and you are happy with the translated text in the ‘Translated Text’ box. You may continue translating other text or shut down your KantanAPI by clicking the ‘Shutdown API’ button.

When you click the ‘Shutdown API’ button a pop-up will now appear asking you ‘Are you sure you want to shout down the API?’ Click ‘OK’.

Shutdown Pop-up alert

The ‘Shutdown API’ button will now change to ‘Terminating API’, the ‘API status’ will now change from ‘running’ to ‘terminating’ and you shouldn’t be able to click on the ‘Translate’ or ‘Retrain Engine’ button.

Terminating API

You will now be directed back to the initial screen on the API Settings page.

API settings page

 

Additional Support

KantanAPI™ is one of the various machine translation services offered by KantanMT to improve  productivity for our clients and also enable them to be more efficient. For more information on KantanAPI or any KantanMT products please contact us at info@kantanmt.com.

For more details on the KantanMT API please see the following links and the video below:

Understanding and Improving your KantanMT Engine with KantanTimeLine™

Ease of use and simplicity are always on the minds of our Developers, hence the making of KantanTimeLine™. KantanTimeLine enables KantanMT clients to view the life cycle of their KantanMT engine. This empowers our clients as they are able to find exactly what is negatively or positively affecting the quality of their engines. Clients are able to keep track of things such as, Training Data uploads, Translation jobs, Engine Tuning, templates, Build jobs and so on through the KantanTimeLine.

How to use KantanTimeLine™

Login into your KantanMT account using your email and your password.

You will be directed to the ‘My Client Profiles’ page. You will be in the ‘Client Profiles’ section of the ‘My Client Profiles’ page. The last profile you were working on will be ‘Active’.

Active profile

If you wish to use ‘KantanTimeLine’ with another profile other than the ‘Active’ profile. Click on the profile that you want to you wish to view the ‘KantanTimeLine’.

Click on the ‘TimeLine’ tab.

TimeLine tab

You will now be directed to the ‘TimeLine’ page for your chosen profile.

TimeLine

To restore an Archived Build select the Build you wish to restore from the ‘Archives’ drop-down menu and click on the ‘Restore’ button.

Archive and Restore

To delete an archived Build click on the ‘Delete’ button.

Delete

To archive a Build click on the ‘Archive’ button of the build you wish to archive.

Archive

To view or edit the description of a build click on the ‘Yellow Notepad’ icon.

Yellow Notepad

To filter the timeline click on the ‘Filter’ drop down-menu and select the filter you wish to use.

Filters

Additional Information and Support

KantanTimeLine™ is one of the many products offered by KantanMT to make  the integration of Machine Translation into the workflow of our clients seamless. For more information on TimeLine or any KantanMT products please contact us at info@kantanmt.com.

TimeLine can also be used in KantanBuildAnalytics. To learn how TimeLine is incorporated into KantanBuildAnalytics please click on the link below or contact us at  info@kantanmt.com.

Get that Customer – Why Machine Translation Works Best for eCommerce Product Descriptions

KantanMT for eCommerceIt’s a fact, infiltrating new markets is the key to increasing profits, and the first item on any company’s internationalization checklist should be to make sure it communicates product information in a way its target customers can understand.

In 2006, Common Sense Advisory (CSA) identified that 73% of consumers read content in their native languages, and 42% prefer to make purchases in their native tongue (Can’t read, won’t buy).

Leading on from the 2006 research, CSA’s updated survey in 2014 was based on a sample of three thousand global respondents, and it reinforced earlier results by showing that 55% only buy from websites in their native language. This jumped dramatically to 80% in cases where the buyers English language ability is limited.

When it comes to selling internationally, tapping into new revenue streams demands translated content. But, what happens when you have thousands of product descriptions that need to be localized into a plethora of languages?

This is where the fun begins for localization teams with well-established traditional translation workflows in place. Their existing method seems fine…but when it’s time to scale up, this is when cracks in the process begin to appear.

The translation workflow works best when it matches the scale and velocity for the content created whether it is product descriptions, manuals or online help documentation.

The challenging part –

How to translate product descriptions with velocity and to scale?

We have heard a great deal of arguments for and against machine translation and one of the most well known against arguments is “the quality is rubbish, sentences translated by machine translation are garbled and incomprehensible”. We in the language technology field hear this frequently and often shudder in disbelief at how these conclusions have been reached.

Generic or free machine translation systems in most cases do not produce great results, expecting such a system to produce publishable quality MT results or using it as benchmark for all MT systems is akin to extracting blood from a stone. Achieving good MT output takes time, care and the ability to customise the MT system properly.

Any company that is serious about breaking into international markets should also be serious about their MT strategy. They should be considering a customised MT solution that is tailored to their needs, not just by going for a cheap and/or supposedly free option.

KantanMT- Machine Translation for product descriptions

Why is MT customisation so important?

Statistical machine translation is based on machine learning and pattern recognition. Segments with multiple word phrases or n-grams as they are known are identified with probability algorithms that select the most probable translation match. Generic or free MT systems typically have been built on a broad mix of content styles and types. This means it’s much harder for the MT system to identify the most likely or even relevant matches in generically built engines.

When the MT system is customised specifically for content that comes from a single domain, such as product descriptions for a specific categories e.g. Home and garden, fashion or electronic devices, the syntax, style and phraseology used will make sure that when an MT match is generated there will be a higher probability that the match will be closer to the desired output, resulting in a much more accurate translation.

How important is saving costs?

Of Course Machine Translation can save costs – if done properly, significant savings can be made. But, saving costs is often not the end goal for implementing a serious MT strategy. The real gains come from increasing productivity without a compromise in quality. Why translate 2000 words a day when you can machine translate and post-edit 8000 words with no loss of quality? Really it can be done! See an example first hand (Netthandelen’s case study PDF download).

When it comes to eCommerce and selling hundreds of products online the words to be translated are counted in billions not thousands, and without MT, traditional localization budgets would become more and more expensive, so MT is really the only practical solution. But, if MT is considered a way to save money by cutting corners then it is doomed to fail from the outset.

It will fail because it’s not sustainable, the effort and costs required to fix bad quality MT output are too great, and if fixing is neglected by publishing the content as is, it will result in angry customers who shop elsewhere – and they will, as the choice available now is greater than ever before!

KantanMT Key Takeaway Key takeaways

  1. Generic free MT will not generate the same quality as customised MT
  2. Investing in a robust MT strategy will save time, costs and headaches in the long run
  3. Keep focus on communicating with the customer, in their language and your eCommerce business will thrive

Email louisei@kantanmt.com if you have questions or want to learn more about how Machine Translation works for product descriptions.

Using F-Measure in Kantan BuildAnalytics

What is F-Measure ?

KantanMT Logo 800x800 F-Measure is an automated measurement that determines the precision and recall  capabilities of a KantanMT engine. F-Measure measures enables you to determine the  quality and performance of your KantanMT engine

  • To see the accuracy and performance of your engine click on the ‘F-measure Scores’ tab. You will now be directed to the ‘F-measure Scores’ page.

F-Measure tab

  • Place your cursor on the ‘F-measure Scores Chart’ to see the individual score of each segment. A pop-up will now appear on your screen with details of the segment under these headings, ‘Segment no.’, ‘Score’, ‘Source’, ‘Reference/Target’ and ‘KantanMT Output’.

Segment

  • To see the ‘F-measure Scores’ of each segment in a table format scroll down. You will now see a table with the headings ‘No’, ‘Source’, ‘Reference/Target’, ‘KantanMT Output’ and ‘Score’.
  • To see an even more in depth breakdown of a particular ‘Segment’ click on the Triangle beside the number of the segment you wish to view.Triangle
  • To reuse the engine as Test Data click on the ‘Reuse as Test Data’. When you do so, the ‘Reuse as Test Data’ button will change to ‘Delete Test Data’.Test Data
    Delete Test Data
  • To download the ‘F-measure Scores’, ‘BLEU Score’ and ‘TER Scores’ of all segments click on the ‘Download’ button on either the ‘F-measure Scores’, ‘BLEU Score’ or ‘TER Scores’ page.download

This is one of the features provided by Kantan BuildAnalytics to improve an engine’s quality after its initial training .To see other features used by Kantan BuildAnalytics please click on the link below .To get more information about KantanMT and the services we provide please contact our support team at  at info@kantanmt.com.