Machine learning won't solve natural language understanding

So Hyperloop should be very likely to occur?

https://leancrew.com/all-this/2013/08/hyperloop/

I think what you're saying is true, but I don't think this kind of ambiguity was really a feature of the examples in the article

Sure. It was an extreme example of the difference between "can't" and "won't", and a point about theory vs practice.

Caveat lector: I'm analysing this as a linguist. Not as a programmer. (Unless you count a bunch of bash scripts as "programming".)

>Let us start first with describing what we call the “missing text phenomenon” (MTP), that we believe is at the heart of all challenges in natural language understanding.

The missing text is not the heart of the challenge; it's just a surface issue. The actual problem is deeper - machines treat words as if they got intrinsic meaning, when the meaning is actually negotiated between speaker and hearer at the moment of the utterance.

This might sound complicated so, as an example, let's say I told you: "I got a cat. That wug sleeps on my bed."

You don't know what's a "wug" (it's a nonsensical word BTW), or why I'm calling my cat a "wug". So you're missing info, just like the machine, right? And yet you're able to parse the second sentence just fine, based on the first. And if we keep chatting about my cats, any mention of the word "wug" will represent the feline from the picture. We effectively negotiated the word "wug" to represent that cat.

A machine does not do that; instead it'll give words intrinsic, non-negotiable meanings. It won't have "wug" in its dataset, so it won't understand that sentence.

I don't believe that machine learning will solve this issue _on its own_, but it could once we're able to simulate that negotiation of meanings.

>Was Aristotle really Aristotle?

If I saw this sentence "in the wild", I'd immediately interpret it as someone questioning the historicity of Aristotle, and claiming his works were made by someone else. It shows that the question is not as redundant as it might look like.

> The trophy did not fit in the suitcase because it was too // 1a. small // 1b. big

This specific example doesn't show it, but that ambiguity is an issue even for human beings, as shown by

"I dropped the trophy on the table. Now it's broken." (What's broken - the trophy, or the table?)

In fact, it's such a big issue that languages often have a bunch of resources to minimise those situations, as gender agreement and distal/proximal pronouns.

Common experience can be inferred from utterances, but difficult until stated, e.g. "the pleasing coolness on the reverse side of the pillow." http://lib.ru/ADAMS/liff.txt

Similar to TFA's compression, if utterances are messages, can we decode them? (i.e. is it possible, not whether computationally feasible).

We need sufficient redundancy, so for example, a one-time pad encoding is impossible to decode (each message is encoded using random information, which sender and receiver both know, that information being shared offline/out-of-band).

So, human beings do have shared offline information, that TFA discusses. Unlike a one-time pad, this information is reused repeatedly. TFA claims the amount of reuse is insufficient for statistical inference, and argues that variations (like bag, suitcase, briefxase) will not be picked up as the same kind of thing (container), thus reducing the amount of reuse.

I think statistically inferring this commonality is feasible, from messages like putting in, taking out sometning etc.

Another argument made is that the message must be perfectly resolved. This is far from true in human communication, where ambiguity is rampant in practice. People routinely clarify as they talk, sometimes realizing later there is a misunderstanding - implicitly, by stating their understanding, sometimes explicitly asking for repetition or clarification.

Part of the skill of written communication, where the reader can't seek clarification, is to strive for clarity, describe the same concept in sifferent ways, give examples - and for very skilled writers, to subtly calibrate readers for the next idea in the process of communicating the previous idea.

But TFA is basically right, that there is a limit to how much shared background information can be inferred from utterances. One example is that technical experts are difficult to understand for humans without that technical background, and mere terminology isn't enough.

Another example is observational comedy, where the auidence understands, though it has never been said before. (from DNA)

    ABILENE (adj.)
     Descriptive of the pleasing coolness on the reverse side of the pillow.

Now, this effect perhaps could be inferred from some characters in stories flipping their pillow on a hot night, or might require a simulation of physics and physiology - a big ask from utterances!

    KENTUCKEY (adv.)
     Fitting exactly and satisfyingly.
     The cardboard box that slides neatly  into an exact space in a  garage, or the  last book which exactly fills a bookshelf, is said to fit 'real nice and kentuckey'.

Some words are funny because of how they sound or their feel in the mouth. Again, difficult to infer, if you have no mouth. I think "kentuckey" is apt in the above because of "tuck", and "ken" somehow makes it funny, but I'm not sure why (maybe a statistical method would know why?). I do seen why the southern phrase at the end is funny.