Language translator

Log in to Vote
403 Votes • 49 Comments
• posted 6 years and 5 months ago • type: Goodie (Perl functions) Needs Source Suggestions

This comment has been removed for violation of our forum rules.
posted by <hidden> • 6 years and 5 months ago
hello, how i can help you for this idea
posted by [UserVoice Mehrez Bentahar] • 6 years and 1 month ago Link
It's done already...!translate
posted by [UserVoice Greg] • 6 years and 6 days ago Link
I've started working on this.
posted by [UserVoice Pieter Bos] • 5 years and 11 months ago Link
However, Google Translate doesn't offer free API access and for example Bing only up to 5000 queries per month. Anyone know a free alternative?
posted by [UserVoice Pieter Bos] • 5 years and 11 months ago Link
Hi Pieter, I used this page: (you pass the string to be translated as a message and the languages in the request) then find in the html response the following: <div class="translateTxt"> (the translation goes here). Happy coding :D
posted by [UserVoice Mauricio Poppe] • 5 years and 11 months ago Link
posted by [UserVoice Anonymous] • 6 years and 1 month ago Link
este o alternativa
posted by [UserVoice Anonymous] • 5 years and 8 months ago Link
What if the user specified the language before typing the word or phrase they want translated? Then, based on the language, you could find some online dictionary site, and get the translation from there? Usually you can just plug it into the url. Example:

The user will type this

japanese: nihongo

Now we know they want Japanese, and a translation of the word nihongo. Using jisho,org, an online dictionary, just input the word into the url like this:***=nihongo&eng=&...

Notice where it says "***=" you put the word after that. Then I'm guessing there's a way to get the info off the webpage from there, but I'm not sure. I'm not much of a web guy, so for me this is just conceptual.
posted by [UserVoice Shaquil] • 5 years and 7 months ago Link
Please accept both from and to languages!
posted by [UserVoice Biep] • 5 years and 5 months ago Link
Anyone using linguee?
It useful because it give you the context of words or small expression you want to translate.
For instance:

It already has several languagues to translate "from" and "to": english, french, german, spanish, portugues

posted by [UserVoice Xav'] • 5 years and 3 months ago Link
Translated foreign page ........ search and translate togather
posted by [UserVoice sultan] • 5 years and 3 months ago Link
We need new source suggestions for this instant answer.

Particularly, we're looking for a source that:

1. Has a high degree of accuracy (many of the crowdsourced translators seem to be low quality)
2. Handles phrases and whole paragraphs, as opposed to just single words.
3. Can translate to many languages (some sources that were suggested can only do a handful of languages)

What does the community recommend?
posted by [UserVoice DuckDuckGo Team] • 5 years and 1 month ago Link
This page can be useful:
It groups different translating systems.

I am not sure about translating whole paragraphs, but for single words, Linguee and Wordreference are great.
I think Wordreference bangs should be extended to all available combinations (with language code associations of 4 letters).
Linguee should be added too, as it is very useful for translations in context.

I guess the ideal would be a crowd-sourced database that can learn from user requests and feedback?
posted by [UserVoice chtfn] • 5 years and 1 month ago Link
Make a duolingo sort of thing?
posted by [UserVoice Anonymous] • 5 years and 1 month ago Link
Language translation is quite hard. Baby steps are in order. Go language by language. Start with just words and phrases.

I wrote an Android app that uses for translation. If the user enters "what is hello in Japanese" I think a plugin can easily handle that, using different websites basef on the language being asked for. it could also be extended to converting from another language to English.
posted by [UserVoice Shaquil] • 5 years and 29 days ago Link
an excellent one but doesn't support evry language
posted by [UserVoice Robert59] • 5 years and 25 days ago Link
Seems like there are two different ideas of what is wanted/needed. Some people are looking for an expedient solution that just pulls results from an existing service (via API or redirect). Others are thinking of an actual translation engine.

This is in my area of expertise, and I would be willing to take on a translation engine project if there were:
- good community support for the idea
- some clear use cases
- at least one compelling reason not to use when a person wanted translation

Google's translation engine is quite good - not perfect, but quite good. Due to the significant manpower that goes into such a project, there should be very clear goals and a strong impetus for the project.

With that said, Apertium is not really suitable for a translation engine with global relevance. It is, as Joop pointed out, good for syntactically similar languages, but this condition is probably not common to the most common uses.

The problem of dealing with dissimilar languages is extremely complex. But, an incremental approach like Shaquil suggested isn't likely to be an ultimately successful strategy. There are a few fundamental issues that need to be worked on before doing anything language-specific. The first is to decided on a syntax-centric approach or a semantics-centric approach. The former is much easier but works much less effectively with dissimilar languages. The second is much more useful but exponentially more difficult. A semantics-centered approach best involves glossing the original text into a language-independent semantic representation.

When this basic approach is established, then you can start to work on mapping individual languages.

I am most interested in working on a semantics-centered approach, as this is where I've done much of my past work. And, I think it's the most useful. The basic approach is not to try to translate from Language A --> Language B, but to to map from Language A --> a gloss (language-independent representation of the meaning) --> Language B. There's a long list of reasons for this.
posted by [UserVoice Brent] • 5 years and 11 days ago Link

By that, do you mean this idea is split into these 2 parts?
1) Direct language translation by searching, "translate: abcd xyz"
2) For instant answers (and organic results) to return relevant results, across languages (e.g. searching in english will return results in spanish, relevant to the translated query).

because this particular idea thread is for #1. It can be attained via an instant answer:

#2 is a general change to the core algorithm for organic links. That said, instant answers can be modified (as they're open source) by anyone and should eventually give returns in any language, if the searcher queried in that language.

Can you clarify a bit so I can point you in the right direction?
posted by [UserVoice Zac] • 5 years and 11 days ago Link
Hi Zac,

Yeah, I was just meaning to say that it seemed that comments were directed toward two distinct sorts of projects:
1) Development of a multilingual translator that was capable of parsing at least to the sentential level (like
2) A much simpler hack that simply leveraged existing third-party solutions to yield results.

There simply aren't any existing public projects that are anything close to meeting all three requirements outlined above - at least, not that are suitable for a wide range of language families and/or for working in arbitrary domains ("domains" in the linguistic sense, not the networking sense). So, any solution either involves uncovering an existing and previously non-public project or starting a new one.

I was just saying that #1 is a very ambitious undertaking and, as such, there should be very clear goals in mind. I love the idea of working on such a project (in fact I've been doing that off-and-on since about 2008). But, even so, I can't come up with a compelling reason not to use to achieve similar results.

I think that, if some compelling counter-cases to could be codified (unintentional alliteration), then it might be feasible to rally the necessary talent to pull it off. I can't overstate, however, what a huge undertaking it is. There are some very real reasons that it has never been done very well.

Many of these reasons could be overcome with well-directed resources. But, unfortunately, this sort of work is generally overshadowed by the observation that:

a) There isn't much money in it (compared to the cost of development).
b) It isn't likely to be so reliable that a human doesn't ultimately have to intervene.
c) In the short-term, it is cheaper and more reliable to just have humans do the work.

... all very valid considerations. However, the more long-sighted view is that comprehensive work in this arena has direct implications to a number of other more taxing problems. Specifically, to do L1-->L2 translation in a way that preserves meaning, this requires algorithms that comprehensively extracts meaning from natural language. And that is a game changer. No one (and I mean "no one" is doing that yet).

So, I would put forward that this is THE most important project for a search engine. But, perhaps not the most appropriate project for DDG which is not the first-line information parser for results. That is, if DDG was parsing original web content directly, and producing results from those primary data, then a semantic parser would be a great asset. Being, actually, a consumer of secondary data and a producer of tertiary data, then it might be that there is no net benefit to end users of building a project that doesn't simply get results from a third party.

I don't know. That's more of a philosophical question to the DDG leadership. It is really a question of whether DDG wants to step out of the role of information middle man. If not, then it probably does not make sense to build a project that doesn't leverage the same model of passing on results from a third party. And, any project that does leverage that model will be quite limited since no one has done a great job at solving this problem yet (with the possible exception of Google).

posted by [UserVoice Brent] • 5 years and 11 days ago Link
Ah ... so maybe I'm looking at this too broadly. This thread was a call for source suggestions for an instant answer multilingual translator.

Sticking to that topic, I can say without reservation that there is NO existing project that meets the stated requirements unless it is being worked on privately and just hasn't shown up on the radar yet. The only decent third party sources are Google (which I don't think offers a useful API for this), and Bing.
posted by [UserVoice Brent] • 5 years and 11 days ago Link
This would be very useful to me, and I would love to have it added.

^By far the best translation I have found (paragraphs). Word Reference is the best single word.
posted by [UserVoice ChillyCurve] • 5 years and 9 days ago Link
On Babylon:
- English <--> French is decent (as expected)
- English <--> Russian is hit-and-miss
- English <--> Arabic is nearly unusable
- English <--> Hebrew is nearly unusable
- Arabic <--> Hebrew is hit-and-miss
- Translation between any other combination of the above is rubbish.
posted by [UserVoice Brent] • 5 years and 6 days ago Link
Spanish is very good. I use it for my Spanish class and it works fine.
posted by [UserVoice ChillyCurve] • 5 years and 2 days ago Link
Thanks, ChillyCurve! We haven't seen that translation service before.

It would be great if everyone who knows more than English could test it. We just ran it by Getty (our German teammate) and he said it's mostly accurate (though people in Germany probably wouldn't speak that way).

Seems usable!
posted by yegg Staff5 years and 8 days ago Link

That source seems to only handle individual words and the community is looking for a full text language translator capable of accurately translating sentences and paragraphs:
posted by yegg Staff5 years and 1 month ago Link
Thanks, Brent!
posted by yegg Staff5 years and 5 days ago Link
Greg, the !bang tags are a separate DDG feature (and not a plugin). This hasn't been created...yet : )
posted by yegg Staff6 years and 5 days ago Link
apertium is a good open source engine for languages that are close one to another.
posted by <hidden> • 5 years and 24 days ago Link
Can non-native English speakers give this a test?

API here:
posted by zac Staff4 years and 9 months ago Link
It seems working good for Polish <-> English translations ;) I recommend it.
posted by NamelessOne Translation Manager4 years and 8 months ago Link
I just typed "translate "new" english to spanish" - I would expect an instant answer. . .
posted by evejweinberg 4 years and 7 months ago Link
posted by <hidden> • 4 years and 4 months ago Link
I know that DDG has some sort of partnership with Yandex, maybe this could be extended to allow DDG to use Yandex's translation service?
posted by GiT 4 years and 4 months ago Link
I also think would be a good idea!

I took a look on the Page code of their searchpage,
and the id of the first word is "tr1".

so by typing for example
you directly get to the first result of "to test".
With this we didn't even need a real API.

The disadvantage is, that i don't know how to set the language you want to translate to.

But maybe we'll find out!
posted by Leso_KN 4 years and 4 months ago Link
Yandex.Translate API docs:

Limited to 10k queries or 1m characters per day, but limits may be enforced on a case by case basis.
posted by kap 4 years and 3 months ago Link
This comment has been removed for violation of our forum rules.
posted by <hidden> • 4 years and 2 months ago
Hi All,

I do a lot of English-Chinese translations for my company, and my typical drill is to type in the word that I would like to translate, followed by the language, into the search engine. For instance:
- "气缸 english"
- "cylinder 中文"

And I will browse through the summarized search results and websites to find the translated word that best suits my use.

I do it in this format because by typing "Chinese" in Chinese ("中文"), the search results will show the Chinese dictionary websites that have better translations.

I think it would be neat if the language translator app can give you the translation in this format:
"(word/phrase you would like to translate) (language you want to translate the world/phrase into)"

P.S. For German, and are great!

posted by <hidden> • 4 years and 2 months ago Link
Bing translate
posted by Salutlolo 4 years and 1 month ago Link
How about using wolfram alpha for this
posted by Choca 3 years and 10 months ago Link
jkanarek seems like the most robust and comprehensive source with free access.
posted by jkanarek Staff3 years and 8 months ago Link
That seems like it would work. 2 million characters a month is enough that it would almost never cost money, and the quality is basically the same as google translate.
posted by <hidden> • 3 years and 6 months ago Link
posted by jkanarek Staff3 years and 8 months ago Link
We're still looking for a free translation API with good coverage. Bing's API uses OAuth, which Spice does not support. Open to source suggestions!
posted by talsraviv 3 years and 6 months ago Link
posted by <hidden> • 3 years and 4 months ago Link
The open source CAT software offers the following translation services:

- Belazar
- Apertium
- Google Translate
- Yandex
- Microsoft

And what about Bablefish?
posted by <hidden> • 3 years and 3 months ago Link
This comment has been removed for violation of our forum rules.
posted by <hidden> • 2 years and 11 months ago
posted by benrob0329 2 years and 9 months ago Link
Hey, I wanted to see if I'm going in the right direction with this. I completed the Instant Answer and it seems to work correctly. I'm wondering if there's a better way to trigger it though. Right now you need to put in something like ice cream in spanish and it will give you the translation.
Here's the module. In order to get the translation you need to put in an abbreviation or the language that is supported by the api. The languages are stored in an array. I'm using yandex translate api.
posted by <hidden> • 2 years and 9 months ago Link