News for hackers. Stuff that matters.
Re:Does Machine Translation Affect International Trade? by dwohnitmok on Sunday September 27, 2020 @09:03PM (#24611762)
Machine translation feels like one of the quiet victories of the current crop of machine learning products.

It's getting to be within spitting distance of being completely adequate (though not excellent) for translating long-form articles, which is amazing considering where things stood ten years ago.

Re:Does Machine Translation Affect International Trade? by klodolph on Sunday September 27, 2020 @10:20PM (#24612309)
For some language pairs, maybe. The problem is that as you translate between more distant languages, you find that something which is contextual in one language is textual in the other, and vice versa.

The neural networks are great at faking it, and they'll make up text that looks completely reasonable all day long. If that means inventing subjects and choosing random verb tenses, that's what they'll do. If you pick closely-related languages, you might be able to get a near perfect translation just by putting each word through a dictionary, and the neural networks can disambiguate things and smooth over the problems in the output by looking at local context. If you pick distantly-related languages, you might routinely need context from paragraphs away, or context which isn't present in the text at all but relies on some kind of human experience.

Re:Does Machine Translation Affect International Trade? by MiroF on Sunday September 27, 2020 @11:11PM (#24612603)
> more distant languages,

low resource translation is definitely still bad, you're right.

> near perfect translation just by putting each word through a dictionary, and the neural networks can disambiguate things and smooth over the problems in the output

Funnily enough, this is not a terrible explanation of how the current sort of approaches to low-resource MT work.

Re:Does Machine Translation Affect International Trade? by thaumasiotes on Monday September 28, 2020 @06:15AM (#24615033)
>> more distant languages,

> low resource translation is definitely still bad, you're right.

No, you've misunderstood. Languages that are closely related to each other are fairly easy to translate between. Languages that aren't related are not, regardless of whether you have a large corpus to work with. English - Mandarin is not an example of "low resource translation".

Re:Does Machine Translation Affect International Trade? by MiroF on Monday September 28, 2020 @11:37AM (#24617779)
> Languages that aren't related are not, regardless of whether you have a large corpus to work with

The size of the corpus makes a huge difference. I don't see how can both be true that a. there is this massive failure of translation engines on these language pairs,

b. human translators were unable to differentiate between human translated chinese-english sentences and machine translated sentences.

It's not incredible - but it's also not awful or unusable.

Re:Does Machine Translation Affect International Trade? by thaumasiotes on Monday September 28, 2020 @07:20PM (#24622322)
> It's not incredible - but it's also not awful or unusable.

If your use case is (1) being vocally excited about machine translation, or (2) having fun in your spare time, then machine translation is good enough for you.

If you have a genuine need to know what something in a foreign language says, machine translation is unusable.

This isn't really a good usability profile.

Re:Does Machine Translation Affect International Trade? by MiroF on Tuesday September 29, 2020 @07:40PM (#24634352)
We successfully use it in production at the company I work for, so this is just (1) not true, (2) an ill-informed opinion.
Re:Does Machine Translation Affect International Trade? by Baeocystin on Sunday September 27, 2020 @09:36PM (#24612034)
I find that machine translation is getting better at producing what reads as grammatically correct text, but that it still misses a lot of what is said, even when the idioms and expressions used are common. Often what is produced is grammatical, but opposite/orthogonal of the initial intent.

In a sense, I feel that this is an even worse situation, because the word-salad signal that it isn't an accurate-meaning translation isn't as strong.

Re:Does Machine Translation Affect International Trade? by userbinator on Sunday September 27, 2020 @10:09PM (#24612252)
That's what MT based on neural networks will do: their output can look great, but the correspondence with the input can be highly inaccurate. On the other hand, traditional methods based on syntactic analysis tend to yield less grammatically correct and more literal translations, but the literalness can also result in better accuracy.
Re:Does Machine Translation Affect International Trade? by MiroF on Sunday September 27, 2020 @11:12PM (#24612609)
Mm... I think you'd be hard pressed at this point to find any advantage that traditional methods have over deep methods.

Maybe this was true 4-6 years ago, but no longer.

Re:Does Machine Translation Affect International Trade? by _-___________-_ on Monday September 28, 2020 @12:36AM (#24613006)
Depends what you optimise for. Neural translation fairly consistently produces incorrect results that read like they could be correct, for me. If your goal is "text that makes sense" they seem to be doing great. If your goal is "text that conveys the same meaning as the source" they're universally rubbish, at least for the language pairs I need (mostly english <-> east Asian languages).
Re:Does Machine Translation Affect International Trade? by MiroF on Monday September 28, 2020 @01:55AM (#24613380)
> english <-> east Asian languages

I'm curious what the domain is and what languages you're talking about, it's hard for me to evaluate your claims otherwise. I would buy it for English -> Tibetan for instance.

Re:Does Machine Translation Affect International Trade? by _-___________-_ on Monday September 28, 2020 @02:08AM (#24613446)
Mostly Chinese, Japanese, and Vietnamese, and mostly business and lightly-technical text.

My observation of the failure rate (if you define failure as "meaning has been lost") is well above 80% with Google Translate for these languages and this type of text.

It's literally unusable because you have no confidence that the translation has not completely reversed or garbled the meaning of the text, and the failure mode is particularly unpleasant because you may be unaware that it has failed to translate correctly, since it produces text that appears to have meaning - just the wrong meaning.

Re:Does Machine Translation Affect International Trade? by MiroF on Monday September 28, 2020 @11:00AM (#24617337)
> It's literally unusable

It's not "literally unusable." Even for language pairs with poor translation, it considerably saves on manual translation time if you can have a translator look over sets of already translated (but lower-quality) sentences and correct those with errors.

Plus, there are actual studies out there comparing human translations to machine translations in a double-blinded evaluation by translators and the gap is not as high as your comment suggests.

For chinese-english (the other direction), bilingual evaluators have had difficulty differentiating between the machine translation and the human translation.

Re:Does Machine Translation Affect International Trade? by _-___________-_ on Thursday October 01, 2020 @08:18AM (#24650023)
> For chinese-english (the other direction), bilingual evaluators have had difficulty differentiating between the machine translation and the human translation.

Having attempted to use CN->EN machine translation many times, I find this very surprising. Have you got a reference I can have a look at?

Re:Does Machine Translation Affect International Trade? by numpad0 on Monday September 28, 2020 @04:12AM (#24614218)
Kinda funny when people say "East Asia" it mostly means Japan and its isolationism, with China mixed in just to change the tone a bit. I don't find it offensive, just kind of funny/interesting.
Re:Does Machine Translation Affect International Trade? by _-___________-_ on Monday September 28, 2020 @04:36AM (#24614373)
Well, in the context of language it's a useful term because of the close relationship many east Asian languages have.
Re:Does Machine Translation Affect International Trade? by numpad0 on Monday September 28, 2020 @05:20AM (#24614661)
Do those languages really have that relationship? When I scratched surface of Chinese language in university it felt almost English written in Kanji. No resemblance to Japanese, and it even made the classical Chinese interpretation methods taught in Japanese education rather dubious to me.
Re:Does Machine Translation Affect International Trade? by thaumasiotes on Monday September 28, 2020 @06:22AM (#24615073)
Japanese and Chinese languages are not related by descent. They differ in many very basic ways.

But Asian languages are nevertheless related in more mysterious ways. Compare the intro to https://en.wikipedia.org/wiki/Mainland_Southeast_Asia_lingui... :

> The Mainland Southeast Asia linguistic area is a sprachbund including languages of the Sino-Tibetan, Hmong–Mien (or Miao–Yao), Kra–Dai, Austronesian and Austroasiatic families spoken in an area stretching from Thailand to China. Neighbouring languages across these families, though presumed unrelated, often have similar typological features, which are believed to have spread by diffusion.

In a European context, this is similar to the unusual closeness between the "unrelated" English and French, known to be due to intensive contact between the languages post-William-the-Conqueror. (In a world context, English and French are closely related regardless.)

Re:Does Machine Translation Affect International Trade? by _-___________-_ on Monday September 28, 2020 @06:20AM (#24615063)
Although they belong to historically disparate language families, modern Vietnamese and Japanese vocabulary both have significant influence from Chinese languages. I know little about Korean but I imagine it's the case there too.

Your comment about Chinese feeling like English written in Kanji is really interesting to me, perhaps it's a case of different perspectives - I tend to focus on grammar when learning a language, and so Chinese feels very different to English from my perspective.

Re:Does Machine Translation Affect International Trade? by 082349872349872 on Monday September 28, 2020 @02:23AM (#24613535)
I strongly prefer the disfluent but more likely accurate results from the old days to the fluent-appearing but of unknown accuracy of today.

https://news.ycombinator.com/item?id=24302564

Bonus clip: https://www.youtube.com/watch?v=0E4aYgKmIko

Re:Does Machine Translation Affect International Trade? by MiroF on Monday September 28, 2020 @11:32AM (#24617714)
"the disfluent but more likely accurate results"

-> Human evaluation does not agree that PBSMT is more accurate than NMT. Sure, the fluency/"sounds good" gains from NMT are much larger than the accuracy gains, but evaluations I've seen put NMT ahead on both metrics.

Re:Does Machine Translation Affect International Trade? by 082349872349872 on Monday September 28, 2020 @11:46AM (#24617905)
Fair enough, this is just my sentiment, where accurate was not a term of art, but meant "honest where it is weak and where it is confident."

Before, I could skim outputs, and get a fair idea of which areas were poorly translated by where it was garbage. Now, I get the impression that (like with GPT or style transfer) something always comes out, whether it's related (or even necessarily has the right negation parity) or not.

Re:Does Machine Translation Affect International Trade? by MiroF on Monday September 28, 2020 @11:54AM (#24617991)
You're absolutely right with your impression of GPT/these models - they will generally generate plausible text.

And it is also worth noting (as you've sort of mentioned) that appearance of fluency can bias translators who are instructed to just evaluate accuracy, or to evaluate accuracy and fluency separately. There is ongoing research into that problem.

Re:Does Machine Translation Affect International Trade? by xbmcuser on Sunday September 27, 2020 @10:01PM (#24612209)
I think the problem is when direct translation is done. Netflix paper using simplify then translating to me seems to be the better approach when you want to convey the meaning rather than just translating the exact words https://arxiv.org/abs/2005.11197
Re:Does Machine Translation Affect International Trade? by danielscrubs on Monday September 28, 2020 @02:19AM (#24613512)
What now? How? It’s getting better by the day but translation is one of the places where it has done more damage than good. It teaches language students incorrect grammar and hinder students from changing their thought pattern.

“- Milk tea or regular tea? -Yes!” Yes is the proper response in some languages. You can either change the language or your mindset.

And it’s not like these things are one offs, all languages are basically a bunch of quirks.

No doubt it’s the way of the future but I’d wait for the researchers to improve translation a lot.

Re:Does Machine Translation Affect International Trade? by _-___________-_ on Monday September 28, 2020 @12:34AM (#24612993)
I really have to disagree. Machine translation is utterly terrible, and appears to be optimising for the wrong thing. All the progress seems to be in making it produce output that makes sense, rather than producing output that conveys the same meaning as the source document. Almost every time I've tried to use machine translation for something serious, the meaning of the text has been garbled or reversed. This is not "adequate" unless your only goal is to produce something that looks like it could be correct, without regard for whether it is.