Microsoft adds Māori to translator as New Zealand pushes to revitalize the language

The benefits of machine translation are easy to see and experience for ourselves, but those practical applications are only one part of what makes the technology valuable. Microsoft and the government of New Zealand are demonstrating the potential of translation tech to help preserve and hopefully breathe new life into the Māori language.

Te reo Māori, as it is called in full, is of course the language of New Zealand’s largest indigenous community. But as is common elsewhere as well, the tongue has fallen into obscurity as generations of Māori have assimilated into the dominant culture of their colonizers.

Māori people make up about 15 percent of the population, and only a quarter of them speak the language, making for a grand total of 3 percent that speak te reo Māori. The country is hoping to reverse the trend by pushing Māori language education broadly and taking steps to keep it relevant.

Microsoft and New Zealand’s Te Taura Whiri i te Reo Māori, or Māori Language Commission, have been working together for years to make sure that the company’s software is inclusive of this vanishing language. The latest event in that partnership is the inclusion of Māori into Microsoft’s Translator service, meaning it can now be automatically translated into any of the other 60 supported languages and vice versa.

That’s a strong force for inclusion and education, of course, since automatic translation tools are a great way to engage with content, check work, explore previously untranslated documents, and so on.

Creating an accurate translation model is difficult for any language, and the key is generally to have a large corpus of documents to compare. So a necessary part of the development, and certainly something the Commission helped with, was putting together that corpus and doing the necessary quality checks to make sure translations were correct. With few speakers of the language this would be a more difficult process than, say, creating a French-German translator.

One of the speakers who helped, Te Taka Keegan from the University of Waikato, said (from this Microsoft blog post):

The development of this Māori language tool would not have been possible without many people working towards a common goal over many years. We hope our work doesn’t simply help revitalize and normalize te reo Māori for future generations of New Zealanders, but enables it to be shared, learned and valued around the world. It’s very important for me that the technology we use reflects and reinforces our cultural heritage, and language is the heart of that.

Languages are dying out left and right, and although we can’t prevent that entirely, we can use technology to help make sure that they are both recorded and capable of being used alongside the dwindling number of active languages.

The Māori translation program is part of Microsoft’s AI for Cultural Heritage program.

Google’s Translatotron converts one spoken language to another, no text involved

Every day we creep a little closer to Douglas Adams’ famous and prescient babel fish. A new research project from Google takes spoken sentences in one language and outputs spoken words in another — but unlike most translation techniques, it uses no intermediate text, working solely with the audio. This makes it quick, but more importantly lets it more easily reflect the cadence and tone of the speaker’s voice.

Translatotron, as the project is called, is the culmination of several years of related work, though it’s still very much an experiment. Google’s researchers, and others, have been looking into the possibility of direct speech-to-speech translation for years, but only recently have those efforts borne fruit worth harvesting.

Translating speech is usually done by breaking down the problem into smaller sequential ones: turning the source speech into text (speech-to-text, or STT), turning text in one language into text in another (machine translation), and then turning the resulting text back into speech (text-to-speech, or TTS). This works quite well, really, but it isn’t perfect; Each step has types of errors it is prone to, and these can compound one another.

Furthermore, it’s not really how multilingual people translate in their own heads, as testimony about their own thought processes suggests. How exactly it works is impossible to say with certainty, but few would say that they break down the text and visualize it changing to a new language, then read the new text. Human cognition is frequently a guide for how to advance machine learning algorithms.

Spectrograms of source and translated speech. The translation, let us admit, is not the best. But it sounds better!

To that end researchers began looking into converting spectrograms, detailed frequency breakdowns of audio, of speech in one language directly to spectrograms in another. This is a very different process from the three-step one, and has its own weaknesses, but it also has advantages.

One is that, while complex, it is essentially a single-step process rather than multi-step, which means, assuming you have enough processing power, Translatotron could work quicker. But more importantly for many, the process makes it easy to retain the character of the source voice, so the translation doesn’t come out robotically, but with the tone and cadence of the original sentence.

Naturally this has a huge impact on expression and someone who relies on translation or voice synthesis regularly will appreciate that not only what they say comes through, but how they say it. It’s hard to overstate how important this is for regular users of synthetic speech.

The accuracy of the translation, the researchers admit, is not as good as the traditional systems, which have had more time to hone their accuracy. But many of the resulting translations are (at least partially) quite good, and being able to include expression is too great an advantage to pass up. In the end, the team modestly describes their work as a starting point demonstrating the feasibility of the approach, though it’s easy to see that it is also a major step forward in an important domain.

The paper describing the new technique was published on Arxiv, and you can browse samples of speech, from source to traditional translation to Translatotron, at this page. Just be aware that these are not all selected for the quality of their translation, but serve more as examples of how the system retains expression while getting the gist of the meaning.

This little translator gadget could be a traveling reporter’s best friend

If you’re lucky enough to get travel abroad, you know it’s getting easier and easier to use our phones and other gadgets to translate for us. So why not do so in a way that makes sense to you? This little gadget seeking funds on Kickstarter looks right up my alley, offering quick transcription and recording — plus music playback, like an iPod Shuffle with superpowers.

The ONE Mini is really not that complex of a device — a couple microphones and a wireless board in tasteful packaging — but that combination allows for a lot of useful stuff to happen both offline and with its companion app.

You activate the device, and it starts recording and both translating and transcribing the audio via a cloud service as it goes (or later, if you choose). That right there is already super useful for a reporter like me — although you can always put your phone on the table during an interview, this is more discreet and of course a short-turnaround translation is useful as well.

Recordings are kept on the phone (no on-board memory, alas) and there’s an option for a cloud service, but that probably won’t be necessary considering the compact size of these audio files. If you’re paranoid about security this probably isn’t your jam, but for everyday stuff it should be just fine.

If you want to translate a conversation with someone whose language you don’t speak, you pick two of the 12 built-in languages in the app and then either pass the gadget back and forth or let it sit between you while you talk. The transcript will show on the phone and the ONE Mini can bleat out the translation in its little robotic voice.

Right now translation online only works, but I asked and offline is in the plans for certain language pairs that have reliable two-way edge models, probably Mandarin-English and Korean-Japanese.

It has a headphone jack, too, which lets it act as a wireless playback device for the recordings or for your music, or to take calls using the nice onboard mics. It’s lightweight and has a little clip, so it’s probably better than connecting directly to your phone in many cases.

There’s also a 24/7 interpreter line that charges two bucks a minute that I probably wouldn’t use. I think I would feel weird about it. But in an emergency it could be pretty helpful to have a panic button that sends you directly to a person who speaks both the languages you’ve selected.

I have to say, normally I wouldn’t highlight a random crowdfunded gadget, but I happen to have met the creator of this one, Wells Tu, at one of our events and trust him and his team to actually deliver. The previous product he worked on was a pair of translating wireless earbuds that worked surprisingly well, so this isn’t their first time shipping a product in this category — that makes a lot of difference for a hardware startup. You can see it in action here:

He pointed out in an email to me that obviously wireless headphones are hot right now, but the translation functions aren’t good and battery life is short. This adds a lot of utility in a small package.

Right now you can score a ONE Mini for $79, which seems reasonable to me. They’ve already passed their goal and are planning on shipping in June, so it shouldn’t be a long wait.

Judge says ‘literal but nonsensical’ Google translation isn’t consent for police search

Machine translation of foreign languages is undoubtedly a very useful thing, but if you’re going for anything more than directions or recommendations for lunch, its shallowness is a real barrier. And when it comes to the law and constitutional rights, a “good enough” translation doesn’t cut it, a judge has ruled.

The ruling (PDF) is not hugely consequential, but it is indicative of the evolving place in which translation apps find themselves in our lives and legal system. We are fortunate to live in a multilingual society, but for the present and foreseeable future it seems humans are still needed to bridge language gaps.

The case in question involved a Mexican man named Omar Cruz-Zamora, who was pulled over by cops in Kansas. When they searched his car, with his consent, they found quite a stash of meth and cocaine, which naturally led to his arrest.

But there’s a catch: Cruz-Zamora doesn’t speak English well, so the consent to search the car was obtained via an exchange facilitated by Google Translate — an exchange that the court found was insufficiently accurate to constitute consent given “freely and intelligently.”

The fourth amendment prohibits unreasonable search and seizure, and lacking a warrant or probable cause, the officers required Cruz-Zamora to understand that he could refuse to let them search the car. That understanding is not evident from the exchange, during which both sides repeatedly fail to comprehend what the other is saying.

Not only that, but the actual translations provided by the app weren’t good enough to accurately communicate the question. For example, the officer asked “¿Puedo buscar el auto?” — the literal meaning of which is closer to “can I find the car,” not “can I search the car.” There’s no evidence that Cruz-Zamora made the connection between this “literal but nonsensical” translation and the real question of whether he consented to a search, let alone whether he understood that he had a choice at all.

With consent invalidated, the search of the car is rendered unconstitutional, and the charges against Cruz-Zamora are suppressed.

It doesn’t mean that consent is impossible via Google Translate or any other app — for example, if Cruz-Zamora had himself opened his trunk or doors to allow the search, that likely would have constituted consent. But it’s clear that app-based interactions are not a sure thing. This will be a case to consider not just for cops on the beat looking to help or investigate people who don’t speak English, but in courts as well.

Providers of machine translation services would have us all believe that those translations are accurate enough to use in most cases, and that in a few years they will replace human translators in all but the most demanding situations. This case suggests that machine translation can fail even the most basic tests, and as long as that possibility remains, we have to maintain a healthy skepticism.

Flitto’s language data helps machine translation systems get more accurate

 Artificial intelligence-powered translation is becoming an increasingly crowded category, with Google, Microsoft, Amazon and Facebook all working on their own services. But tech still isn’t a match for professional human translations and machine-generated results are often hit-and-miss. One online translation service, Flitto, is now focused on providing other companies with the language… Read More

800M Facebook users see automatic language translations each month

fb-wit Machine learning is accomplishing Facebook’s mission of connecting the world across language barriers. Facebook is now serving 2 billion text translations per day. Facebook can translate across 40 different languages in 1800 directions like French to English. And 800 million users, almost half of all Facebook users, see translations each month. Alan Packer, Facebook’s Director… Read More

10 text, sentiment, and social analytics trends for 2016

10-text-sentiment-social-analytics-trends-2016

Text, sentiment, and social analytics help you tune in, at scale, to the voice of the customer, patient, public, and market. The technologies are currently being applied in an array of industries ranging from healthcare to finance, media, and consumer markets. They distill business insight from online, social, and enterprise data sources.

It’s useful stuff, insight extracted from text, audio, images, and connections.

The state of analytics is pretty good at the moment, although uptake in certain areas — digital analytics and market research, for example — has lagged behind. But even in areas of strong adoption such as customer experience, social listening, and engagement, there’s room for growth. This is true for both technical innovation and for more-of-the-same uptake. This still-growing market space means opportunity for new entrants and established players alike.

We could examine each analytics area in isolation, but it’s better to look at the combined impact, as the technologies and applications overlap. Social analyses that neglect sentiment are incomplete, and to get at online, social, and survey sentiment, you really need text analytics.

This article, a look-ahead technology and market assessment, surveys high points for the year to come, with a run-down of 10 text, sentiment, and social analytics trends to watch for in 2016.

Multi-lingual is the rule

While English-only analytics holdouts remain, and it’s certainly better to do one language really well than to cover many poorly, machine learning (ML) and machine translation have facilitated the leap to multi-lingual analytics, making it the new norm. But if you do need to work across languages, do some digging: Many providers are strong in core languages but weak in others. Choose carefully.


Join VB Insight for “How to Spell Success Everywhere in the World”
How to increase sales, loyalty, and engagement through localization and translation
Sign up now from anywhere (with Internet).


Text analysis gains recognition 

Text analysis capability is a key solution for customer experience, market research, and consumer insights, and for digital analytics and media measurement — and providers are increasingly competing on the merits of their analytics. Build or subscribe: both are viable options. While you could call this trend point quantified qualitative, what really matters is that text analysis is baked into the business solution.

Machine learning, stats, and language engineering coexist.

Tomorrow belongs to deep learning — to recurrent neural networks and the like — but for today, long-established language-engineering approaches still prevail. I’m referring to taxonomy, parsers, lexical and semantic networks, and syntactic-rule systems. So we have a market where “a thousand flowers bloom, a hundred schools of thought contend…” and these many approaches can coexist. Cases in point: Even crowd-sourcing standard-bearer CrowdFlower is embracing machine learning, and startup Idibon makes a selling point of combining the traditional and the new: “You can construct custom taxonomies and tune them with machine learning, rules, and your existing dictionaries/ontologies.”

Image analysis enters the mainstream. 

Leading-edge providers are already applying image analysis tech to decipher brand signals in social-posted media — check out Pulsar and Crimson Hexagon — and image analysis ability, via deep learning, was a major selling point in IBM’s 2015 AlchemyAPI acquisition. Indeed, hot ML start-up Metamind pivoted in 2015 from NLP to a focus on image analysis, as it recognized the extent of the opportunity.

A breakout for speech analytics, with video to come.

The market loves to talk about omni-channel analytics and about the customer journey, which involves multiple touchpoints. And, of course, social and online media are awash in video. The spoken word — and non-textual speech elements, including intonation, rapidity, volume, and repetition — carry meaning, accessible via speech analysis and speech-to-text transcription. Look for breakout adoption in 2016, beyond the contact center, by marketers, publishers, and research and insights professionals. Expect speech analytics to also serve as an enabler for high-accuracy conversational interfaces.

Expanded emotion analytics.

Advertisers have long understood that emotion drives consumer decisions, but, until recently, broad, systematic study of reactions has been beyond our reach. Enter emotion analytics, either a sentiment analysis subcategory or sister category, depending on your perspective. Affective states are extracted from images and video via facial-expression analysis (or from speech or text), with the aim of quantifying our emotional reactions to what we see, hear, and read. Providers include AffectivaEmotient, and Realeyes for video, Beyond Verbal for speech, and Kanjoya for text; adopters in this rapidly expanding market include advertisers, media, marketers, and agencies.

ISO emoji analytics.

Given that we have text, image, speech, video, and Likes — why use emoji? Because they’re compact, easy to use, expressive, and fun! Like #hashtags, they complement and add punch to longer-form content. That’s why Internet slang is dead (ROFL!) and Facebook is experimenting with emoji Reactions, and — more of a good thing –we’re seeing variants like Line stickers. What’s needed now is emoji analytics. The tech for this area is emerging via startups such as Emogi. (Check out Emogi’s illuminating 2015 Emoji Report). Although most others don’t go beyond counting and classification to get at emoji semantics — the sort of analysis done by Instagram engineer Thomas Dimson and by the Slovene research organization CLARIN.SI — some of these, for instance SwiftKey, deserve a look.

Deeper insights from networks plus content

This is both a 2016 trend point and most of the title I gave to a 2015 interview with Preriit Souda, a data scientist at market-research firm TNS. Preriit observes, “Networks give structure to the conversation while content mining gives meaning.” Insight comes from understanding messages and connections and how connections are activated. So add a graph database and network visualization tools to your toolkit — there’s good reason Neo4jjs, and Gephi (to name a few open-source options) are doing well. Building on a data-analytics platform such as QlikView is another option, one that can be applied in conjunction with text and digital analytics: a to-do item for 2016.

In 2016, you’ll be reading (and interacting with) lots more machine-written content.

The technology for machine-written content is called natural language generation (NLG) and provides the ability to compose articles — and email, text messages, summaries, and translations — algorithmically from text, data, rules, and context. NLG is a natural for high-volume, repetitive content: financial, sports, and weather reporting. Check out providers ArriaNarrative ScienceAutomated InsightsData2Content, and Yseop. You can also look to the machine’s end of your conversation with your favorite virtual assistant — with Siri, Google Now, Cortana, or Amazon Alexa — or with an automated customer-service or other programmed response system. These latter systems fall in the natural-language interaction (NLI) category; Artificial Solutions is worth a look.

Machine translation matures.

People have long wished for a Star Trek-style universal translator, but while 1950s researchers purportedly claimed that machine translation was a problem that would be a solved within three or five years, accurate, reliable MT has proved elusive. (The ACM Queue article Natural Language Translation at the Intersection of AI and HCI nicely discusses the machine translation state of the human-computer union.) I wouldn’t say that the end is in sight, but thanks to big data and machine learning, 2016 (or 2017) should be the year that major-language MT is finally good enough for most tasks. That’s an accomplishment!

Every one of these trends will affect you, whether directly — if you’re a text, sentiment, or social analytics researcher, solution provider, or user — or indirectly, because analysis of human data is now woven into the technology fabric we rely on every day. The common thread is more data, used more effectively, to create machine intelligence that changes lives.


SethGrimes-square500Seth Grimes is an analytics strategy consultant with Washington DC based Alta Plana Corporation. He is founding chair of the Text Analytics Summit (2005-13), the Sentiment Analysis Symposium, and the LT-Accelerate conference in Brussels.










Localization at scale: Being relevant to your customers wherever they are (webinar)

flags localization

Join us for this live webinar on Tuesday, September 29 at 9 a.m. Pacific, 12 p.m. Eastern. Register here for free.

While technology has paved the road to localization, it’s the expectations of today’s users that are pushing companies to location-based relevance at a faster pace — particularly with a generation that’s come of age with the technology.

“Millennials and GenY’s are expecting to have things that are local,” says Dave Fish, SVP, Expert Services of the customer experience company MaritzCX and one of our upcoming panelists tomorrow. “They prefer to buy groceries that are sourced locally and they prefer to know the people they’re dealing with rather than dealing with a big anonymous corporate entity.”

It’s this kind of thinking that is creating a challenge for companies providing localized experiences and communication — at scale. That gets even more complicated when you’re in the context of going global, where cross-cultural considerations can spell mammoth success or embarrasing failure.

“If you’re not communicating using local language or idioms, you can be very off-putting,” says Fish. “What can be a good engagement can turn into something that’s very, very negative. So it’s a requirement nowadays rather than a nicety.”

It’s why for Fish, the experience is what it all comes down to. Whether you’re one of the 3,000 micro-breweries across the U.S. trying to express that unique pride of place, or a global brand appealing to a vast market, you need to be able to cross the great divide with ease.

“You have a brand that stands for something — and that should be translatable across cultures and langauges and local markets,” says Fish. It can come down to specific channels and what works and doesn’t in different countries.

“In some countries, you can do email, in some countries, you can’t,” he explains. “In some you can do telephone, in some you can’t and in some you can do mail, some you can’t — so just picking the right modality to communicate is important.”

And while Fish believes that the role of Chief Customer Experience Officer is now essential to organizations — and many are rolling that out in various ways — localization can be boiled down to something rather simple.

“It’s really just a subset of segmentation,” he says. “Just a different way of looking at people.”

Join us tomorrow as Fish will join Stewart Rogers, VB Insight’s Director of Marketing Technology for an important discussion on what’s needed to get localization right, whether it’s the next state, or the next continent.
They’ll be sharing tips not just on the process, but on how to deliver better metrics to senior leadership to communicate the true story of your brand’s globalization.


Don’t miss out!

Register here for free.


In this webinar, you’ll learn how to:

  • Re-think campaign creation at the regional level — and the global one
  • Effectively use in-market experts to drive better impact
  • Make your branding as world-ready as possible.
  • Use metrics to show the truest picture of your campaign’s effectiveness
  • Enhance the customer experience through added local flavor

Speakers:

Stewart Rogers, Director of Marketing Technology, VB Insight

Dave Fish, SVP, Expert Services, MaritzCX


This webinar is sponsored by Lionbridge.

 

More information:

Powered by VBProfiles










Localization and translation: The biggest mistakes you’re probably making (webinar)

the world

Join us for this live webinar on Tuesday, September 29 at 9 a.m. Pacific, 12 p.m. Eastern. Register here for free. 

International marketing fails are legendary — and show that even mega brands can blunder big time when they try and take campaigns beyond familiar borders.

When Pepsi tried to introduce the slogan “Come alive with the Pepsi Generation” into China, the translated message apparently was read in Chinese as “”Pepsi brings your ancestors back from the grave.”

“Got milk?” — the famously successful tagline for the California Milk Processing Board — didn’t go over so well in Mexico. The Spanish version was interpreted as “Are you lactating?”

The need to get localization and translation right is more urgent than ever as digital and mobile brands can cross geographies at lightening speed compared to companies producing packaged goods. With a digital commodity that’s gaining traction, breaking down geographic doors is the next logical step. But it’s not just about translation (although you certainly want to get that right).

It’s far more about understanding the cultural differences that are going to help you break into that next lucrative market. How you onboard customers may vary differently from one region to the next. Monetizing tactics may vary considerably as different markets can respond distinctly. And the user experience may need to be adapted accordingly.

This webinar will help you understand how you can truly “think global and act local”. VB Insight’s Director of Marketing Technology Stuart Rogers and a stellar panel will share essential best practices and tips on how to approach the vagaries of international marketing in a tech-driven age.


Don’t miss out!

Register here for free.


In this webinar, you’ll learn how to:

Re-think campaign creation at the regional level — and the global one
Effectively use in-market experts to drive better impact
Make your branding as world-ready as possible.
Use metrics to show the truest picture of your campaign’s effectiveness
Enhance the customer experience through added local flavor

Speakers:

Stuart Rogers, Director of Marketing Technology, VB Insight

Dave Fish, SVP, Expert Services, MaritzCX


This webinar is sponsored by Lionbridge.

 

More information:

Powered by VBProfiles










Localization and translation: The biggest mistakes you’re probably making (webinar)

the world

Join us for this live webinar on Tuesday, September 29 at 9 a.m. Pacific, 12 p.m. Eastern. Register here for free. 

International marketing fails are legendary — and show that even mega brands can blunder big time when they try and take campaigns beyond familiar borders.

When Pepsi tried to introduce the slogan “Come alive with the Pepsi Generation” into China, the translated message apparently was read in Chinese as “”Pepsi brings your ancestors back from the grave.”

“Got milk?” — the famously successful tagline for the California Milk Processing Board — didn’t go over so well in Mexico. The Spanish version was interpreted as “Are you lactating?”

The need to get localization and translation right is more urgent than ever as digital and mobile brands can cross geographies at lightening speed compared to companies producing packaged goods. With a digital commodity that’s gaining traction, breaking down geographic doors is the next logical step. But it’s not just about translation (although you certainly want to get that right).

It’s far more about understanding the cultural differences that are going to help you break into that next lucrative market. How you onboard customers may vary differently from one region to the next. Monetizing tactics may vary considerably as different markets can respond distinctly. And the user experience may need to be adapted accordingly.

This webinar will help you understand how you can truly “think global and act local”. VB Insight’s Director of Marketing Technology Stuart Rogers and a stellar panel will share essential best practices and tips on how to approach the vagaries of international marketing in a tech-driven age.


Don’t miss out!

Register here for free.


In this webinar, you’ll learn how to:

Re-think campaign creation at the regional level — and the global one
Effectively use in-market experts to drive better impact
Make your branding as world-ready as possible.
Use metrics to show the truest picture of your campaign’s effectiveness
Enhance the customer experience through added local flavor

Speakers:

Stuart Rogers, Director of Marketing Technology, VB Insight

Dave Fish, SVP, Expert Services, MaritzCX


This webinar is sponsored by Lionbridge.

 

More information:

Powered by VBProfiles