Anyone who has ever used Google translate knows that the translated version is mostly grammatically correct but often extremely awkward to use in a conversation.

This is one of the factor which has prohibited it from gaining wider usage, i.e. sending your Spanish friend a letter written completely in Google translated Spanish.

Actually this is the reason I am asking the question in the first place. I need to email a professor in Mexico, I forgot how to say something along the lines of "I need something could you do me a favor" in a natural way in Spanish. I got something very awkward from Google translate and has been trying to revise it in a more natural language ever since.

Do you think Google translate will ever have the potential to translate language at a level where humans actually communicate? What are some of the challenges preventing this?

4 Answers 4


MT is hard. Google Translate is based on statistical methods with models trained on large bilingual corpora. There are a few rule-based systems that produce better translations but only in closed specialized domains. As for now nobody has an algorithm or method that performs better.

It's impossible to predict the future but I wouldn't hope for significantly better translations in the next years.

  • Are you saying that google translate uses machine learning to figure out how things work?
    – Fraïssé
    Jan 25, 2015 at 5:24
  • Yes, they use statistical models trained on parallel corpora. That's why they have wide coverage but using SMT means that only limited context is considered.
    – Atamiri
    Jan 25, 2015 at 5:44

Your question makes some broadly misleading assumptions about both translation and machine translation.

The problem here is not "grammatical" correctness. It's not a problem for Google to generate superficially grammatical sentences. But sentences only appear as part of text/utterance which is the really carrier of communicative meaning. Any one word or phrase only makes sense in that context. Also, texts have their own idiomatic conventions which depend on many factors.

So you have to evaluate MT (machine translation) at the level of the whole text, utterance or conversation. And here you find that often the coherence breaks down. You see translations of texts where there are multiple contradictory interpretations of an event/situation in the target text that are not present in the source text.

The reason is that unlike with a human translation, machine translation does not start with a thorough understanding of the source text. It combines some basic parsing with stochastic methods - essentially dealing with probabilities based on huge corpora.

But because language is basically infinitely variable, even the vast corpora at Google's disposal are not enough to guess at the right equivalents for every sentence. This becomes exponentially more difficult because most sentences only make sense in the context of other sentences. Current MT has almost no way of evaluating the role of context in disambiguation and has to pretty much stay at the level of single sentences with some basic anaphoric parsing.

It is hard to predict the future of MT but replacing human translators and interpreters is not even on the horizon. I suspect that NLP is very near the peak of the gains that can be made through stochastic processing in the same way it reached the end of what can be done with pure parsing twenty years ago. It will keep improving incrementally but the field is waiting for a new breakthrough.


Google Translate uses machine learning. Unlike human translation, it uses parsing of simple text and other stuff.

But Google's corpora is not enough to make the translation the same as how people translates. This becomes a challenge and MT will not really get through the field where it's almost the same as how a human translates by spending years of improvement just to make it a little bit better each time but still trying to get to the field.

It's still possible to make it better always but not to when it is good to replace human translators.


The challenge is figuring out how human language works, in detail. If we knew that, we could program top-notch translate programs and do lots of other neat things.

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Not the answer you're looking for? Browse other questions tagged or ask your own question.