nadiatims Wrote:what happens if you ask one of the AIs "When did WW2 start?" or something anyone with access to wikipedia can easily check?
Can you really answer questions like that just with statistical text analysis?

Yep, it's been done. https://www.google.co.uk/search?q=when+did+wwii+start

Well, if giving the answer in the form of a webpage strikes you as a copout, I think Google is working on their own sort of knowledge database that's probably a bit closer to what you're thinking of.

dizmox Wrote:Yep, it's been done. https://www.google.co.uk/search?q=when+did+wwii+start

Or this: http://www.wolframalpha.com/input/?i=When+did+WW2+start?

dizmox Wrote:I guess this is straying away from the topic of machine translation, I don't think anything nearly as powerful as an AI that could beat the Turing test would be needed for 99% accurate machine translation.

Back to the Turing test though: feed all the communication history of mankind into a machine with the the most sophisticated of text analysis algorithms conceivable if you want - it might be a fantastic oracle, but it will still be easily outed as a machine by someone asking the right questions - ones that rely on its lack of understanding of the real world (and more generally, anything) and its inability to deal with novel scenarios.

Maybe it could you fool into thinking it's an extremely dull witted human who didn't have an intelligent opinion on any new situation described to it mid-conversation (and thus wouldn't be able to just mindlessly search its data banks for one), but I'd argue that's not really in the spirit of the test.

The Turing test is a weird thing though. In reality, almost any crappy chatbot will pass the Turing test if the person talking to it has no reason to believe they are talking to a computer. So if you don't tell people that they might be talking to a computer, even simple programs can pass the turing test.

Likewise, if you do a regular Turing test (i.e., people know they might be talking to computers) using people who don't know much about computers and AI, a fairly good program will pass the Turing test.

But if you use people knowledgable about the Turing test, as well as computers and AI, almost any program will fail the Turing test.

My favorite is the backwards Turing test. I read a blog many years ago at the end of the chat era, and the blogger said that someone had posted his Yahoo chat name as being an interesting bot. Of course, it was really him, a human. He got a lot of messages from people who thought he was a bot, and try as he might he was unable to convince most of them that he was in fact a human.

Anyway, I don't know why you think a computer that can pass the Turing test needs to be more powerful than a computer that can do extremely accurate machine translation.

Tzadeck Wrote:Anyway, I don't know why you think a computer that can pass the Turing test needs to be more powerful than a computer that can do extremely accurate machine translation.

I guess since I was considering the severe interpretation of the Turing test

Quote:But if you use people knowledgable about the Turing test, as well as computers and AI, almost any program will fail the Turing test.

which seems like a significantly harder problem.

turvy Wrote:What about Chinese <-> English?

I can't test this myself, but from what I can gather with my risible knowledge of Mandarin and common sense, I think it translates much better than whatever you can get from Japanese.

This is the first paragraph of a "Beauty and the Beast" storybook, translated from Chinese to English:

A long time ago, in a tower buildings, a magnificent castle, there lived a young prince.Prince live a prosperous life, to have everything he wants, but he is a cruel and selfish, no love.A stormy night, a ragged old woman came to the castle of the prince, she said: please let me borrow one night.Prince coldly rejected her.

(The original:
很久很久以前，在一座塔樓林立，富麗堂皇的城堡裡，住着一位年輕的王子。王子過着富足的生活，擁有他想要的一切，可他卻是一個冷酷自私，毫無愛心的人。一個風雨交加的夜晚，一位衣衫襤褸的老婆婆來到王子的城堡，她說：請讓我借住一晚吧。王子冷酷地拒絕了她。)

That's just about good enough that it just needs some editing by a native speaker, but it also doesn't have any really complex sentences in it.

Mandarin Chinese is pretty straightforward with word order, and it tends to specify subjects more than Japanese does, though the lack of articles and tense marking pose some problems.

Splatted Wrote:... use of a search engine may allow the computer to find several possible ways of translating a word or phrase, but what criteria does it use to evaluate these choices? If this was a game of chess the criteria would be obvious, whether it leads to a win, a loss or a draw, but no such criteria exist for translation, so I fail to see how the computer could make a reliably good decision.

What if the program searched for corresponding context for all of the possible translations and then selected the translation that occurs most often in similar contexts to the phrase that needs to be translated?

For example, we want to translate 「空気が悪い」. Probably the two most common meanings of this phrase are "the air is stale" (i.e. literally uncomfortable to breathe) or "there is tension in the air". A good MT program would look at the context of 「空気が悪い」 and the compare it to all other contexts in which 「空気が悪い」 is used, and then select the translation that most often occurs in similar contexts (of course, this presumes that the input field doesn't include just the phrase 「空気が悪い」 by itself). For example, if the preceding context mentions a fight or dire situation, then MT program will choose "there is tension in the air". However, if the context refers to dust, difficulty breathing, or a need for fresh air, then the program will choose "the air is stale".

I'd imagine such a program would need to somehow search its database for similar contexts and determine the probability that a certain translation is the most appropriate one given its context. However, it doesn't seem as insurmountable of a problem as it initially may seem.

I don't think anyone has brought this up yet, but one of the big problems with translation is that you need to know a lot to do it. I'm not talking about context, but actually information about the stuff you're translating. For instance, you can't be a technical translator if you don't know anything about computers. I imagine you can't translate legal stuff if you don't know anything about the law. This is a relatively big hurdle for computer translation.

Also, as I'm sure Jarvik and the other translators on this board can attest to, translating is very difficult. Even for someone with years of experience, I'm sure there are some things very difficult to translate.

I'm sure we'll start to see a lot of other impressive advances in AI before we see impressive machine translation. Maybe stuff like bots that can write essays for homework, bots that can play GO, etc.

For a Turing test, if I ask it three obscure questions and it gets them right, does it fail the test? Unless it is a Jeopardy winner, I wouldn't expect a real person to get the answers right.

tetsujin Wrote:For a Turing test, if I ask it three obscure questions and it gets them right, does it fail the test? Unless it is a Jeopardy winner, I wouldn't expect a real person to get the answers right.

Programs made for the Turing test are made to imitate real humans. What makes you think the program would answer obscure questions? If you asked it an unreasonable question for a human, like a complicated math problem, it should say, "Are you kidding? I don't know the answer to that."

Also, a program failing or passing the Turing test is determined by the percentage of people it fools, not whether or not it fools one person.