Goggle Works to Understand Language

April 27, 2018

Back in the day, Google used to do this annoying thing that if you were searching in a foreign language it would translate the word into English. It was difficult to search for foreign language Web sites using Google, unless you went to one of the foreign language Web site endings. Google eventually fixed the “feature”, but the search engine giant is doing something new with searches and translation. Google Translate now tries to understand query text meanings and build responses using natural language.

Forward.com has more information on the new development in the article, “Google Translate For Yiddish? It Ain’t Work Bupkis.” After a brief history lesson about psychologist Frank Rosenblatt and how an AI finally beat world go champion Ke Kie, we finally get into the how of the new Google Translate. The new neural network is a great upgrade, but here are the bugs:

“Although Google Translate’s new approach sounds like a giant leap forward it creates all sorts of problems. To begin with every text must first be translated into English before it can be rendered into another language. Secondly, instead of warning that it doesn’t recognize a certain word the new system automatically inserts its own “creative” meanings in a second-rate imitation of human neural processing.”

In other words, Google Translate still does not have the human comprehension necessary to translate words and sentences accurately to the satisfaction of a person familiar with a language’s nuances. The human mind is still the better language tool and if you are translating using Google Translate, especially Yiddish, keep a dictionary on hand.

Whitney Grace, April 27, 2018

Real Time Translation: Chatbots Emulate Sci Fi

April 16, 2018

The language barrier is still one of the world’s major problems. Translation software, such as Google Translate is accurate, but it still makes mistakes that native speakers are needed to correct. Instantaneous translation is still a pipe dream, but the technology is improving with each new development. Mashable shares a current translation innovation and it belongs to Google: “Google Pixel Buds Vs. Professional Interpreters: Which Is More Accurate?”

Apple angered many devout users when it deleted the headphone jack on phones, instead replacing it with Bluetooth headphones called AirPods. They have the same minimalist sleek design as other Apple products, but Google’s Pixel Buds are far superior to them because of real time translation or so we are led to believe. Author Raymond Wong tested the Pixel Buds translation features at the United Nations to see how they faired against professional translators. He and his team tested French, Arabic, and Russian. The Pixel Buds did well with simple conversations, but certain words and phrases caused errors.

One hilarious example was when Google translated the Arabic for, “I want to eat salad” to “I want to eat power” in English. When it comes to real time translation, the experts are still the best because they can understand the context and other intricacies, such as tone, that comes with human language. The professional translators liked the technology, but it still needs work:

“Ayad and Ivanova both agreed that Pixel Buds and Google Translate are convenient technologies, but there’s still the friction of holding out a Pixel phone for the other person to talk into. And despite the Pixel Buds’ somewhat speedy translations, they both said it doesn’t compare to a professional conference interpreters, who can translate at least five times faster Google’s cloud.”

Keep working on those foreign language majors kids. Marketing noses in front of products that deliver in my view.

Whitney Grace, April 17, 2018

Google Translate Gets a Needs Improvement on Its Translation System

February 5, 2018

I read “The Shallowness of Google.” The critique is not from a trendy start up in Silicon Valley or an academic who flopped in a Google interview. The analysis is by Douglas Hofstadter. if the name does not ring a bell, this is the fellow who wrote Gödel, Escher, Bach, a quite fun read.

The main point of the write up is that Google’s implementation of its artificial intelligence and machine learning technology for Google Translate is bad.

Image result for alpha sled dog

Google wants to be perceived as the alpha dog in smart software. Do you want to take this canine’s kibble? Google can bite even thought it may not get the whole “idea” and “understanding” behind a reprimand.

Mr. Hofstadter writes:

Having ever more “big data” won’t bring you any closer to understanding, since understanding involves having ideas, and lack of ideas is the root of all the problems for machine translation today. So I would venture that bigger databases—even vastly bigger ones—won’t turn the trick.

The idea is that “understanding” is not baked into Google Translate. In addition to providing examples of screwing up translations from French, German, and Chinese, Google Translate does not look up information in Google Search. Mr. Hofstadter does.

He points out:

Google Translate can’t understand web pages, although it can translate them in the twinkling of an eye.

He correctly observes:

As long as the text in language B is somewhat comprehensible, many people feel perfectly satisfied with the end product. If they can “get the basic idea” of a passage in a language they don’t know, they’re happy.

Mr. Hofstadter touches upon two issues, which another informed critic might convert to a write up in the Atlantic:

  1. Google is simply delivering “good enough” services. The object is advertising, not outputting on point products and services for a tiny fraction of its user base
  2. Google’s hype about its smart software is only slightly less off-the-wall than the marketing of IBM Watson. The drum beat for smart software is necessary to attract young programmers who might otherwise defect to Amazon or other Google competitors and to further the illusion that Google’s technology is magical, maybe otherworldly and definitely the alpha dog in the machine learning Iditarod.

The write up is worth reading. However, I would not run it through Google Translate if you prefer to ingest the article in one of Google Translate’s supported languages.

And for a person going through the Google interview process, it is not a plus to suggest that Google’s technology might be little more than a C or possible an F. Rah rah is a better choice.

That’s why we love Google Translate here in Harrod’s Creek, but we have switched to Free Translations.org since Google implemented a word limit.

Stephen E Arnold, February 5, 2018

Privacy Is Lost in Translation

October 30, 2017

Online translation tools are a wonder!  Instead of having to rely on limited dictionaries and grammars, online translation tools deliver real-time, nearly accurate translations of documents and other text.  It is usually good to double check the translation because sometimes the tools do make mistakes.  Translation tools, however, can make mistakes that lose privacy in translation.  Quartz tells an alarming story in, “If You Value Your Privacy, Be Careful With Online Translation Tools.”

Norwegian state oil company Statoil used Translate.com to translate sensitive company documents.  One would think that would not be a problem, except Translate.com stored the data in the cloud.  The sensitive documents included dismissal letters, contracts, workforce reduction plans, and more.  News traveled fast in Norway, resulting in the Oslo Stock Exchange blocking employees’ access to Translate.com and Google Translate.

It was dubbed a massive privacy breach as private documents from other organizations and individuals were discovered.  Translate.com views the incident differently:

Translate.com sees things a little differently, however, saying it was straight with users about the fact that it was crowdsourcing human translations to improve on machine work. In a Sept. 6 blog post responding to the news reports, the company explained that in the past, they were using human volunteer translators to improve their algorithm, and during that time, had made documents submitted for translation public so that any human volunteers could easily access them. ‘As a precaution, there was a clear note on our homepage stating: ‘All translations will be sent to our community to improve accuracy.’

Translate.com also offered to remove any documents upon request, but sensitive documents were still available when the Quartz article was written.  Vice president of Sales for Translate.com Maria Burud pointed out that they offer a paid translation software intended for businesses to maintain their privacy.  Burud notes that that anything translate using a free web tool is bound to have privacy issues, but that there is a disclaimer on her company’s Web site.  It is up to the user to de-identify the information or watch what they post in a translation box.

In other words, watch what you translate and post online.  It will come back to haunt you.

Whitney Grace, October 30, 2017

Instantaneous Language Translation in Your Ear

June 21, 2017

A common technology concept in cartoons and science-fiction series is an ear device that acts as a universal translator.  The wearer would be able to understand and speak any language in the world.  The universal translator has long been one of the humanity’s pipe dream since the Tower of Babel and as technology improves we could be closer to inventing it.  The Daily Mail shares, “The Earpiece That Promises To Translate Language In Seconds: £140 Will Be Available Next Month.”

International travelers’ new best friend might be Lingmo International’s One2One translator that is built on IBM Watson’s artificial intelligence system.  Unlike other translation devices, it does not reply on WiFi or BlueTooth connectivity.  It supports eight languages: English, Japanese, French, Italian, Spanish, Brazilian, Portuguese, German, and Chinese (does that include Mandarin and Cantonese?).  If the One2One does not rely on the Internet, how will it translate languages?

Instead, it uses IBM Watson’s Natural Language Understanding and Language Translator APIs, which intuitively overcomes many of the contextual challenges associated with common languages, as well as understanding the nuances of local dialects…This allows it to translate what you’re saying, almost in real-time.

Lingomo might be relying on IBM Watson for its natural language API, they should also consider using Bitext, especially when it comes to sentimental analysis.  Some languages have words with multiple meanings that change based on a voice’s inflection and tone.

The ramifications for this device are endless.  Can you imagine traveling to a foreign country and being able to understand the native tongue?   It is the dream of billions, but it could also end some serious conflicts.

Whitney Grace, June 21, 2017

Maybe Trump Speak Pretty One Day

June 15, 2017

US President Donald Trump is not the most popular person in the world.  He is a cherished scapegoat for media outlets, US citizens, and other world leaders.  One favorite point of ridicule for people is his odd use of the English language.  Trump’s take on the English tongue is so confusing that translators are left scratching their heads says The Guardian in, “Trump In Translation: President’s Mangled Language Stumps Translators.”  For probably the first time in his presidency, Trump followed proper sentence structure and grammar when he withdrew the US from the Paris Accord.   While the world was in an uproar about the climate change deniers, translators were happy that they could translate his words easier.

Asian translators are especially worried about what comes out of Trump’s mouths.  Asian languages have different root languages than European ones; so direct translations of the colloquial expressions Trump favors are near impossible.

India problems translating Trump to Hindi:

‘Donald Trump is difficult to make sense of, even in English,’ said Anshuman Tiwari, editor of IndiaToday, a Hindi magazine. “His speech is unclear, and sometimes he contradicts himself or rambles or goes off on a tangent. Capturing all that confusion in writing, in Hindi, is not easy,’ he added. ‘To get around it, usually we avoid quoting Trump directly. We paraphrase what he has said because conveying those jumps in his speech, the way he talks, is very difficult. Instead, we summarise his ideas and convey his words in simple Hindi that will make sense to our readers.’

Indian translators also do Trump a favor by translating his words using the same level of the rhetoric of Indian politicians.  It makes him sound smarter than he appears to English-speakers.  Trump needs to learn to trust his speechwriters, but translators should learn they can rely on Bitext’s DLAP to supplement their work and improve local colloquialisms.

Whitney Grace, June 15, 2017

 

Online Translation Becomes a Joke

April 26, 2017

I am not much of a TV buff. I noted the article “Anne Hathaway Sang the Most Awkward Google Translations Beautifully on Jimmy Fallon.” I noted that I will survive was allegedly translated as “I will be punctual.” Close, right. The image below shows the original lyric and Google Translate’s version:

image

Online translation definitely loses none of the nuance and emotional impact. Ooops ooops. When that artificial intelligence controls autonomous drones, what could go wrong? Answer: Nothing. Perfect.

Stephen E Arnold, April 27, 2017

Google: Translation King?

March 1, 2017

I read “Google’s AI Software Wins Top Score among Machines in Translation Battle.” Good news for the GOOG. The company recently limited free online translation, and I noted when I was translating a test passage from Persian to English that the free Google system truncated the passage, a problem which did not plague the FreeTranslatioins.org system. Persian is a bit more of hill climb than translating Spanish to Italian, but the unpredictable behavior was telling.

The write up, however, encountered no glitches it seems. I learned:

Artificial intelligence language software by US Internet giant Google Inc., scored higher than its rival AI machines in a translation battle between humans and machines held in South Korea [in February 2017].

The Google system made kimchi of four human translators, Systran (a go to fave for many years), and the Naver system (anyone remember Naver search?).

The Google system performed well, according to the “real” news outfit Korea Herald:

the organizers said the four professional translators scored better in translating random English articles — literature and non-literature — into Korean and other Korean articles into English than the machines. Of the machines, Google scored a total of 28 out of 60, followed by Naver’s automated translation app called Papago with 17 and Systran with 15, the tech company officials with knowledge of the matter said.

Yikes. Humans did better. No guaranteed annual income for these folks.

Who lost the battle? Systran International.

The factoid I noted was: “The new systems considered an “entire sentence as one unit.”

But humans? Better.

Stephen E Arnold, March 1, 2017

IQwest IT Steps Up Its Machine Translation Marketing

February 3, 2017

Machine translation means that a computer converts one language into another. The idea is that the translation is accurate; that is, presents the speaker’s or writer’s message payload without distortion, odd ball syntax, and unintended humor. What’s a “nus”? The name of a nuclear consulting company or a social mistake? Machine translation, as an idea, has been around since that French whiz Descartes allegedly cooked up the idea in the 17th century.

I read two almost identical articles, which triggered by content marketing radar. The first write up appeared in KV Empty Pages as “Finding the Needle in the Digital Multilingual Haystack.” The second article appeared in the Medium online publication as “Finding the Needle in the Digital Multilingual Haystack.”

image

image

Notice the similarity. Intrigued I ran a query for IQwest. I noted that the domain name IQwest.com refers to a bum domain name. I did a bit of poking around and learned that there are companies using IQwest for engineering services, education, and legal technologies. The IQwest.com domain is owned by Qwest Communications in Denver.

The machine translation write up belongs to the IQwestIT.com group. No big deal, of course, but knowing which company’s name overlaps with other companies’ usage is interesting.

Now what’s the message in these two identical essays beyond content marketing? For me, the main point is that a law firm can use software translation to eliminate documents irrelevant to the legal matter at hand. For documents not in the lawyer’s native language, machine translation can churn out a good enough translation. The value of machine translation is that it is cheaper than a human translator and a heck of a lot less expensive.

Okay, I understand, but I have understood the value of machine translation since I had access to a Systran based system years ago. Furthermore, machine translation systems have been an area of interest in some of the government agencies with which I am familiar for decades.

The write up states:

building a model and process that takes advantage of benefits of various technologies, while minimizing the disadvantages of them would be crucial. In order to enhance any and all of these solution’s capabilities, it is important to understand that machines and machine learning by itself cannot be the only mechanism we build our processes on. This is where human translations come into the picture. If there was some way to utilize the natural ability of human translators to analyze content and build out a foundation for our solutions, would we be able improve on the resulting translations? The answer is a resounding yes!

Another, okay from me. The solution, which I anticipated, is a rah rah for the IQwest machine translation system. What’s notable is that the number of buzzwords used to explain the system caught my attention; for instance:

  • Classification
  • Clustering
  • N grams
  • Summarization

These standard indexing functions are part of the IQwest machine translation system. That system, the write up notes, can be supplemented with humans who ride herd on the outputs and who interact with the system to make sure that entities (people, places, things, events, etc.) are identified and translated. This is a slippery fish because some persons of interest have different names, handles, nicknames, code words, and legends. Informed humans might be able to spot these entities because no system with which I am familiar is able to knit together some well crafted aliases. Remember those $5,000 teddy bears on eBay. What did they represent?

The write up seems to be aimed at attorneys. I suppose that group of professionals may not be aware of the machine translation systems available online and for on premises installation. For the non attorney reader, the write up tills some familiar ground.

I understand the need to whip up sales leads, but the systems available from Google and Microsoft, to name just two work reasonably well. When those systems are not suitable, one can turn to SDL or Systran, to name two vendors with workable systems.

Net net: My thought is that two identical versions of the same article directed at a legal audience represents a bit of marketing wonkiness. The write up’s shotgun approach to reaching attorneys is interesting. I noticed the duplication of content, and my hunch is that Google’s duplicate detection system did as well.

Perhaps placing the write up in an online publication reaching lawyers would be a helpful use of the information?  What’s clear is that IQwest represents an opportunity for some motivated marketing expert to offer his or her services to the company.

My take is that IQwest offers a business process for reducing costs for litigation related document processing. The translation emphasis is okay, but the idea of making a phone call and getting the job done is what differentiates IQwest from, for example, the GOOG. I remember Rocket Docket. A winner. When I looked at that “package,” the attorneys with whom I spoke did not care about what was under the hood. The hook was speed, reduced cost, and more time to do less dog work.

But the lawyers may need to hurry. “Lawyers Are Being Replaced by Machines That Read.” Dragging one’s feet technologically and demanding high salaries despite a glut of legal eagles may change the game and quickly.

Plus, keep in mind FreeTranslations.org. You can get voice translations as well as text translations. The increasingly frugal Google has trimmed its online translation service. Sigh. The days of pasting lengthy text into a box is gone like a Loon balloon drifting away from Sri Lanka.

There are options, gentle reader.

Stephen E Arnold, February 3, 2017

Google and Its Smart Chinese Translation Neural Machine Thing

October 5, 2016

Google has a new neural translation system for Chinese. Read more here. It sort of works, but poetry is not its strong suit. Many Chinese student memorize Shi Jing’s “Cry of the Ospreys.” In Chinese, the first line of the poem is:

image

Google produces this translation of the line:

“Guan guanju dove, in the river of the continent.”

image

A standard English translation is:

Guan, guan, trill the ospreys, upon the island in the creek.

The standard English translation makes evident the sound of the ospreys from the island in the creek. Google sticks in a “dove” and dumps the island. Close enough for ospreys if not making the meaning clear to a non Chinese reader. Shi Jing is not around to offer an opinion which is probably a good thing.

Stephen E Arnold, October 5, 2016

Next Page »

  • Archives

  • Recent Posts

  • Meta