Category Archives: MT in everyday life

Google Translate in a fourth-grade classroom

Leave a reply

I teach the fourth grade in a public elementary school in the suburbs of a large U.S. city, and in my classroom I often have a child or two with very limited English skills. These kids are 8 or 9 years old and often here with parents who are stationed temporarily in the U.S. They get daily or weekly time with the ESOL (English for Speakers of Other Languages) teacher, but other than that, they are fully integrated into normal American classrooms.

I use Google Translate with these children in a very focused, need-to-solve-a-problem basis. I have a specific question I need to ask, an instruction I need them to follow, or I need to get information from them. Things like, How are you going home today? Are you going to buy lunch in the cafeteria today or did you bring a lunch? You know, the kinds of daily activities in the life of a classroom.

When I was in the third grade my dad got posted in a foreign country for a year, so I actually know what it’s like for those kids. You’re just sitting there in a fog while everyone around you speaks Russian or some language you can’t grasp. Nowadays I have a tool I can use to help kids in a similar situation through the school day: Now we’re going to do this. This is what you need to do. Those kinds of things are important for their general feeling of well-being, that they can manage the school day.

Julia_GT excerptI sometimes use it in other ways. During writing lessons, I might have a child write in their native language. Then I copy/paste that into Google Translate so I have an idea of what they’ve written. I figure at this stage, writing in your own language is better than trying to write in English. I’ve even tried translating larger blocks of text for a student to read so they can at least know what is being discussed in class.

The languages I’ve dealt with so far are French and Spanish. I had Latin in high school so I can recognize word derivations and root words and can be somewhat assured that what’s been translated is moderately close to what we’re talking about.

When you’re communicating this way, you have to read between the lines a bit. It’s usually so situation-specific that you can get the meaning, but once in a while it takes some back-and-forth questions and answers to narrow things down and get an understanding. Luckily if we hit a dead end, I usually have a backup: a school employee or another child who speaks the student’s language. If that method fails, we can always call the parents to sort things out. At least one of them usually speaks English.

As the kids learn more English, I find myself using machine translation more. I can tell that they are starting to understand me a bit and I want to communicate more. I first say something then I type it into Google Translate. They can see the connection between what I’m saying, what I’m typing, and then what it goes out to in their own language.

I feel like machine translation is a resource that I can use to move to the next step. It really feels like a bridge for understanding.

Whatever else happens, I want these kids to feel like they are understood.

Gary, developer of MT systems

Leave a reply

I use Google Translate to translate Chinese spam messages which regularly get posted on my website – just in case any of them are of interest!

Actually most of my interest in MT is not about free online MT tools like Google Translate, but about professional tools. I created my first rule-based MT system over 25 years ago and have been involved in developing machine translation since then. My main project is a commercial neural MT system for translating  between Dutch and English. But I also experiment in neural systems for other languages, most recently Indonesian and Turkish.

Since my own knowledge of Indonesian and Turkish is very poor, I’ve found a use for online MT in this experimental work too. For example, I could translate something into Indonesian with my own engine, then back-translate it through Google into English to see how well my model has learned the patterns of a new language. Other times I simply translate the same thing using both my own and Google’s engines and compare the results. It helps me check that my neural network building is going in the right direction.

I really do also Google-translate Chinese spam messages. The translations are usually very basic but tell me what I want to know about the spam – mostly that this is not something in which I could be remotely interested. Let’s not forget that before the arrival of online MT, companies would spend large sums of money each year translating documents that turned out to be completely useless. Online MT saves money.

In general I’m happy to recommend MT to friends for general information purposes: double-checking the translation of a menu in a Chinese restaurant, translating the instructions sent with self-assembly furniture, or reading spam. Most general online translators are quite capable of fulfilling such tasks nowadays. I also recommend MT as a language learning tool.

However, I would not rely on unchecked, unedited MT for information I need to make important decisions. Apart from the obvious fact that the machine translation may be fluent yet incorrect, we have to allow for the possibility that a decision may be challenged in the courts. (Example case. See MT use in the news for more links to news stories on the use of MT).

One thing I’d like people to understand and remember is that the best results are obtained when the MT system is “trained” to handle the type of texts being translated. In online tools like Google Translate, this is not the case.

Krista, language and communications professional

Leave a reply

My English, French and Swedish are all strong and I studied them at the university, but German, Italian and Spanish are languages I haven’t studied since high school. I have a university degree in translation and I worked as a professional translator for some years, but for the past 15 years I’ve been more of a communications professional. I am the Managing Director of a national non-governmental organization and my job consists mostly of communications.

Rich use of Google Translate

I’ve been using Google Translate for many years now. Not in translation work, of course, but for a variety of other things. First of all, I use it to help me make sure I understand texts that are in languages I am not fully fluent in. I read articles, newspaper stories and research papers that have to do with my industry and are in a variety of languages. When I come across a passage I’m not sure I understand, I google-translate it into my native language of Finnish and also into English (usually both, not sure why…maybe curiosity? Or because I love languages?) I also want to know what similar organizations to mine are doing around Europe so I find myself google-translating web pages or other documents to be able to read them.

Sometimes I use the tool to help me when I have to write something in Swedish, which I struggle with a bit. I might write a piece and test it out in Google Translate to make sure I got the phrasing and spelling right. I also test it in regular Google to see if it’s a common way of expressing what I’m trying to express.

I guess the funny thing is that my most frequent use of Google Translate is not really for its translation function. I most often use it as a dictionary. I don’t have a good electronic dictionary at my disposal and I’m a bit lazy about looking things up in books. So I either google the word or use Google Translate to find the meaning. I don’t really look at the translation but down below, where they give dictionary-type information. Here’s an example:

GT dictionary

I like that it gives me multiple suggestions for a translation. I couldn’t ever see myself simply taking the 1 translation it gives in the box and using that. More context helps me make sure I understand.

This also works very well as a thesaurus, a bilingual one at that. It gives you optional synonyms in both languages. And one more thing, a feature I noticed just this year! The megaphone icon at the bottom of the word boxes? That is a pronunciation audio tool.

These kinds of language tools are included in many online dictionaries in different languages, but this is an easy option for multiple languages. Quick.

Oh, and I don’t know if you’ve noticed or not, but they want people to help develop Google Translate. I’ve done some volunteering there, mostly in English since that’s the easiest. You click through expressions and words and see if they’re correct or not. It’s kind of a game and helps to develop it. It’s fun.

Double-checking

Google Translate is hardly ever the only thing I use to verify the meaning of a text; normally I double-check it some other way. Even though it’s just for my own use, I work hard to get a good translation.

First of all, I only use it with languages I know well or at least a little. By comparing the original text and the translation, I know enough to know if the translation is something it’s supposed to be. I would never use it with languages like Arabic or Chinese because I would have no way of knowing how ‘right’ the translations are. I also try out translations with different language combinations, often including English somewhere. Because I have background knowledge on how machine translation works, I know that it works best when English is one of the languages used.

Another way I verify things is by putting them into regular Google. If I can see the same phrase and how it’s used in different contexts, then it can help me fully understand it. Usually when this happens it’s because I’m reading things that are not as familiar to me, like academic or technical texts.

The question of machine translation

I don’t go around recommending the use of machine translation to other people, no. Most often that’s because people need a translation for a text they want to give to someone else or publish. Then I recommend that they use a human translator, of course, because that is what is needed. I think it’s important to make sure people understand that. Another reason I don’t do it is that, if I were to recommend it to someone outside of the language industry, I can’t be sure that person understands the limits of machine translation.

If someone asks me for advice on using it, say they just want to understand a short paragraph, then I tell them it is useful for that if they understand the risks involved. But I’ve never recommended it as such.

When I first started using machine translation it was a bit of a shameful thing. The attitude in the translation community was definitely negative. I didn’t dare tell people I was using it. Nowadays it seems more acceptable for the purposes I use it for. I suppose in earlier years, up to 2010, people were afraid that machine translation would take all the work from translators and eventually they wouldn’t be needed. But now I think people understand it’s just a tool that can’t do everything we need humans to do. I noticed the shift in attitude sometime around 2014 or 2015. It was discussed in conferences in a different way and people were much more interested in the topic.

 

Anne, classical singing, and Google Translate

1 Reply

I Google-translate old Italian arias and not-quite-as-old German lieder.

For the past 8 years I’ve been taking lessons in classical singing. Part of being able to perform a song is to first ‘get inside’ it – understand what kind of message is involved and what the emotion and atmosphere surrounding it are like. Since the songs are often in languages I know only a little (German) or not at all (old Italian), I’ve found it helpful to start the process by putting the lyrics into Google Translate and translating them.

aria lyrics

When we start work with a new song, my teacher often plays the melody for me and sometimes also tells me a little bit about what it’s about. After that I try to find out more. First I check to see if I can find some kind of translation. Many of the songs have been used in teaching classical singing for a long time, so once in a while there is some kind of translation online. However, they can be surprisingly hard to find.

At first I tried looking up everything word-by-word in a dictionary, but that was slow and not that successful. You would have to know the modern equivalents of words in an old language to be able to look them up, and I couldn’t do that. When I put the whole thing into Google Translate, there were words here and there that didn’t get translated, but I still got a general idea of what it was saying.

I’ve used this method since then with new songs. If I can capture some key words – maybe a word is repeated throughout the song, or it’s emphasized somehow or used at a high point in the melody – and get an understanding of those, that is a good start, even if I don’t get a full understanding of the entire song.

I also often translate into both English and my native language of Finnish. Doing it into 2 languages is a good method – you might get something in one of the languages that the other didn’t succeed at, so between the 2 you end up covering mostly everything. And given the options of no understanding or some understanding, I’ll take the latter.

Also, of course Google Translate does not produce a beautiful narrative like the original, but I don’t expect it to. The original is old poetry, after all, and that is difficult even for human translators. What I need is to understand a bit of what it’s about and capture some keywords.

Once a pretty funny thing happened where I found out I had completely misunderstood the translated lyrics of a song I was working on. It was in German and there was just one word I didn’t understand so I put it into Google Translate. Something about the translation of that one word gave me the impression that the speaker in the poem was a woman who was just content to be dancing around with other country folk. It turned out that it was actually about a man who was somewhat lewd and disgusting!

Finally one day I was singing it with my teacher and a pianist. We got to talking about what it’s about, what the feeling and atmosphere should be during each part of the song. I told my teacher what I thought it was and she corrected me. Whereas my earlier rendering had been slightly solemn and serious, after the explanation I understood the humor and playfulness of the poem and was able to match the slightly mischievous tone much better. It became much more fun.

Dr. C. Koby, Physicist*

Leave a reply
Oak Ridge National Laboratory, Tennessee, USA
October 15, 1971

Part of my work as a physicist is to keep abreast of research being carried out in my field. I try to follow activities in all parts of the world, but I am particularly interested in the research being conducted in the Soviet Union. I would guess that something like 15% of the articles and books I need to read in my field are written in Russian. I have no competence in Russian so have to rely on translations to access those materials.

A very positive development in the past few years is a service that my laboratory offers which machine translates articles from Russian to English. They don’t have anyone correct the articles,  you get what the machine puts out. I have personally used the service 10 or so times over the past 3½ years.

I have one simple reason for using the MT service: it is fast. After a request, I can expect to get a machine-translated article back in 1 month, much more quickly than the 9-10 weeks some colleagues report waiting for articles translated by humans.

More time and effort is required to understand machine-translated texts as compared to those written in English – I’d say about double the time. One reason for that is that formulas and diagrams from the original articles do not get translated, so I usually have both the machine-translated text and the original Russian article, and I go back and forth between them. In general, however, I’d say that the quality of the translations is acceptable. In a funny way, over time you get used to the style. You find yourself mentally correcting awkward passages.

I think it’s important to bring up the fact that the machine translation is understandable to myself and my colleagues mostly because we are familiar with the contexts being discussed. We know our own fields well and that allows us to accommodate texts that are not perfect. It is also important that technical terms are translated correctly or at least understandably, and the majority of the time, they are. The most common problem is words that are left untranslated. I don’t know why that happens but it does, and it can affect understanding.

I’ve been asked if it would be possible for someone to completely misunderstand the machine translations and arrive at the opposite meaning from the original. Yes, sometimes the meaning is a bit distorted, but since I know the context of what I’m reading so well, I do not think that it is possible to arrive at the opposite meaning. I have never heard of it happening anyway.

Overall, I’d say that I’m happy to use the service. It allows me to read things I would normally have to wait far longer to get access to. I would, and actually have been known to, recommend the use of machine translation to my colleagues.

*       Instead of being about 1 real person, the persona in this story is a composite that is based on a group of 58 real people who were surveyed by Bozena Henisz-Dostert in the early 1970s (see reference below). The group consisted of some of the first users of one of the first machine translation systems: the Georgetown Automated Translation system, developed in the 1950s and early 1960s at Georgetown University. Although its development was discontinued in 1964 due to lack of financial support, the Georgetown system continued to be used, virtually in its 1964 state, for a decade or so by 2 groups of scientists in Oak Ridge, Tennessee and Ispra, Italy.

The persona in the story was compiled in a straightforward way. I used 23 of the survey’s 51 questions. For each question, I took the most popular answer, or the mean or average of the figures given in answers, to describe Dr. Koby. The name ‘Koby’ came from an internet name generator and does not reflect any one true person.

The story is based entirely on information from Bozena Henisz-Dostert’s article ‘Users’ evaluation of machine translation’ in the book Machine Translation by Henisz-Dostert et al. 1979.