Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Machine learning won't solve natural language understanding

thegradient.pub

Post reply on HN
Print view View original

181–190 of 193 posts

Re: Machine learning won't solve natural language understanding

#181

Post by silent_cal »

darawk wrote: post #179
silent_cal wrote: post #176

Earlier quoted context omitted.

1. Well said, but I would press it further and say that there is at least a pathway for us (human beings) to determine what the actual meaning of the utterance is by considering the context, the speaker, by asking for clarification, and so forth. The problem for the probabilistic/empirical language model is that it can't ever recognize "one right answer", even in theory. That's a problem, because there really is one…

1. Yes, that's true. However i'm not sure I see clearly the distinction you're trying to draw here. You could build a neural network that can ask clarifying questions too. You can certainly define an ML model that recognizes one right answer as well: just pick the answer that has highest probability in your softmax output. 2. Well, there are a lot of ways to do this in principle, but word vectors in their original fo…

1. I'm thinking of it in terms of two different kinds of knowledge that we're going after when we try to (A) understand a proposition vs (B) make a probabilistic guess at the right answer from among a discrete range of possibilities. However our understanding of language works, it's not the same as flagging a maximized probability. If someone says "the bank is on Fifth Street next to the fire hydrant", you immediately know all kinds of things when you take this in - that you're getting directions, that you will soon be looking for a fire hydrant, the address of the bank, that the speaker knows the area pretty well... this big "bundle of truth" emerges from the proposition immediately when we take it in. I just don't see it as analogous to flagging the highest softmax probability score, which at best provides a "most likely" translation into SQL code or a vector, or something like that.

2. If we're introducing concepts like insertion into the model, aren't we then returning to a logical (as opposed to a probabilistic/statistical) language model? Or said differently, aren't we merely introducing our own understanding of language into the model before it's even trained?

Re: Machine learning won't solve natural language understanding

#182

Post by namlem »

HarHarVeryFunny wrote: post #168
namlem wrote: post #145

GPT-3 seems to refute these arguments. It is able to solve most understanding tasks reasonably well.

Perhaps, but "being able to do X" isn't the same as "being able to do X, using approach Y". After all, Deep Blue could play chess more than reasonably well, but no-one would suggest that it understood chess anymore than a calculator understands math. So, is GPT-3 more like a brute force calculator like Deep Blue (or AlphaGo for that matter), or is it more like a human in it's ability to "understand" language ? Given…

AlphaGo is not merely a brute force calculator and neither is GPT-3. They have conceptual representations. That is the advantage of deep neural networks, the ability to form concepts, as biological neural networks do.

Re: Machine learning won't solve natural language understanding

#183

Post by suifbwish »

sdenton4 wrote: post #84
suifbwish wrote: post #67

Earlier quoted context omitted.

The main problem with using stat models or approaches such as deep learning is not that we are unable to do it. Though possibly trivial, the real problem is we are unable to understand how or why it works which can lead to unintended consequences or lack of ability to support/continue further development (aside from not being able to leverage the new fundamental understanding and apply it to related fields). Imagine…

/because enough of the right minds have not been looking at it as a puzzle worth solving, possibly because it and other AI related concepts are often introduced at or just before the PhD level and so most minds in science never encounter it/ Well, there was a good fifty plus years of linguists without access to good statistical methods who also failed to solve the problems as well... And they also didn't come up with…

50 plus years was before the modern computing era. You mean they couldn’t figure it out on paper.

Re: Machine learning won't solve natural language understanding

#184

Post by suifbwish »

Isinlor wrote: post #139
suifbwish wrote: post #67

Earlier quoted context omitted.

The main problem with using stat models or approaches such as deep learning is not that we are unable to do it. Though possibly trivial, the real problem is we are unable to understand how or why it works which can lead to unintended consequences or lack of ability to support/continue further development (aside from not being able to leverage the new fundamental understanding and apply it to related fields). Imagine…

We can understand how and why neural networks work. The issue is that obtaining this understanding requires a lot of effort. OpenAI invested in trying to understand how a simple CNN works. You can read their results here: https://distill.pub/2020/circuits/ > In the original narrative of deep learning, each neuron builds progressively more abstract, meaningful features by composing features in the preceding layer. In…

Thank you for sharing that. Definitely going to read

Re: Machine learning won't solve natural language understanding

#185

Post by HarHarVeryFunny »

namlem wrote: post #182
HarHarVeryFunny wrote: post #168

Earlier quoted context omitted.

Perhaps, but "being able to do X" isn't the same as "being able to do X, using approach Y". After all, Deep Blue could play chess more than reasonably well, but no-one would suggest that it understood chess anymore than a calculator understands math. So, is GPT-3 more like a brute force calculator like Deep Blue (or AlphaGo for that matter), or is it more like a human in it's ability to "understand" language ? Given…

AlphaGo is not merely a brute force calculator and neither is GPT-3. They have conceptual representations. That is the advantage of deep neural networks, the ability to form concepts, as biological neural networks do.

They can form their own internal vector* representations, but they are still fixed architecture. Training AlphaGo can't change it from an RL architecture to something else, nor can training GPT-3 change it from a transformer into a more general cognitive architecture such as human brain.

The datapath through a transformer is entirely prescribed. Once the weights are trained, feeding a test sample into in will indeed just result in a fixed series of calculations to produce an output.

* It's a bit of a stretch to assert that deep neural nets are creating conceptual representations. For example if you look at the early layers of a CNN, what it's learned are just primitive (orientated edge, etc) feature detectors. At higher levels the more primitive features are combined into more complex ones, but they are just visual patterns, not concepts. It'll be the same for AlphaGo - it'll be creating it's own representations of complex board positions. Better than Deep Blue having to work with a human-design board representation, but at the end of the day it is nothing more than a board/position representation.

Re: Machine learning won't solve natural language understanding

#186

Post by darawk »

silent_cal wrote: post #181
darawk wrote: post #179

Earlier quoted context omitted.

1. Yes, that's true. However i'm not sure I see clearly the distinction you're trying to draw here. You could build a neural network that can ask clarifying questions too. You can certainly define an ML model that recognizes one right answer as well: just pick the answer that has highest probability in your softmax output. 2. Well, there are a lot of ways to do this in principle, but word vectors in their original fo…

1. I'm thinking of it in terms of two different kinds of knowledge that we're going after when we try to (A) understand a proposition vs (B) make a probabilistic guess at the right answer from among a discrete range of possibilities. However our understanding of language works, it's not the same as flagging a maximized probability. If someone says "the bank is on Fifth Street next to the fire hydrant", you immediatel…

> 1. I'm thinking of it in terms of two different kinds of knowledge that we're going after when we try to (A) understand a proposition vs (B) make a probabilistic guess at the right answer from among a discrete range of possibilities. However our understanding of language works, it's not the same as flagging a maximized probability. If someone says "the bank is on Fifth Street next to the fire hydrant", you immediately know all kinds of things when you take this in - that you're getting directions, that you will soon be looking for a fire hydrant, the address of the bank, that the speaker knows the area pretty well... this big "bundle of truth" emerges from the proposition immediately when we take it in. I just don't see it as analogous to flagging the highest softmax probability score, which at best provides a "most likely" translation into SQL code or a vector, or something like that.

I certainly agree that it doesn't feel analogous, but i'm not sure that it's as clearly distinct as it intuitively seems. Certainly for most utterances you and I can imagine several plausible alternative interpretations. We are just very good at discerning the right one quickly and accurately, which means that we experience that determination as certainty, rather than probability. But that doesn't necessarily mean that we are perfectly collapsing it to a single meaning right away. In fact for many sentences, the meaning may change completely by adding/removing a word from the end, e.g.:

https://en.wikipedia.org/wiki/Garden-path_sentence

These are obviously not typical of all language, but I don't think it's unreasonable to say that all language in some sense behaves this way, and these types of sentences just make it unusually apparent to us.

> 2. If we're introducing concepts like insertion into the model, aren't we then returning to a logical (as opposed to a probabilistic/statistical) language model? Or said differently, aren't we merely introducing our own understanding of language into the model before it's even trained?

Sort of. This gets into some tricky territory about what concepts are, and what language actually is. But I think if you play around with word vectors a bit, you'll get a sense of what I mean here. Here's a good article summarizing some of their properties:

https://kawine.github.io/blog/nlp/2019/06/21/word-analogies....

You can see that in some sense conceptual essence is being captured statistically here. You can represent concepts as embeddings in a statistical space, where the angles within that space capture relationships between them. It gets kind of difficult to reason about exactly what this "is", but, such is the difficulty in using language to analyze and dissect language.

There can sometimes be a bit of a Homunculus fallacy that underlies the way people reason about language, concepts, and thinking, and I think the original article here is guilty of that. That is, people assert the presence of some immaterial essence to human reasoning or cognition in an implicit way, but don't really justify or define it. Like, what is the concept of 'insertion' really? Intuitively it feels like it has some essence that exists outside of its relations to other concepts. But the only thing we can truly directly talk about is its relationship to other concepts. In this sense, we can say that any given concept is defined by its relation to every other concept. Reifying this abstract notion in the language of mathematics, we can define this as angles in Hilbert space (though it's important to note, that this is not an assertion of essence, merely a descriptive and useful formalism). When we do things like that it tends to feel like these statistical/mathematical descriptions are not "really" capturing meaning, and while I don't want to positively assert that they are necessarily, I do want to challenge the idea that this is obviously true on its face. I think the evidence for this claim is actually pretty weak, when you really analyze it.

I found this article to be very helpful in thinking about a lot of these issues:

https://www.lesswrong.com/posts/9iA87EfNKnREgdTJN/conceptual...

Re: Machine learning won't solve natural language understanding

#188

Post by silent_cal »

darawk wrote: post #186
silent_cal wrote: post #181

Earlier quoted context omitted.

1. I'm thinking of it in terms of two different kinds of knowledge that we're going after when we try to (A) understand a proposition vs (B) make a probabilistic guess at the right answer from among a discrete range of possibilities. However our understanding of language works, it's not the same as flagging a maximized probability. If someone says "the bank is on Fifth Street next to the fire hydrant", you immediatel…

> 1. I'm thinking of it in terms of two different kinds of knowledge that we're going after when we try to (A) understand a proposition vs (B) make a probabilistic guess at the right answer from among a discrete range of possibilities. However our understanding of language works, it's not the same as flagging a maximized probability. If someone says "the bank is on Fifth Street next to the fire hydrant", you immediat…

1. I'd agree it's not "right away", so I think my use of "immediately" as too strong a word. But it sounds like we both agree that the experience of what happens when we are in the process of understand a proposition is different from the "experience" (if you can call it that) of flagging the highest probability.

2. I also agree with you that the perception of relations of things is primary in the way we know things, and it is pretty amazing how word vectors seem to capture some of these relationships in an analogous way (king - man + woman = queen). But I also think we see the properties of things before we see their relations to each other - otherwise, how could you know there is a relationship, not knowing that there are at least two things or properties to relate? But I'm going too far afield now!

Re: Machine learning won't solve natural language understanding

#189

Post by namlem »

HarHarVeryFunny wrote: post #185
namlem wrote: post #182

Earlier quoted context omitted.

AlphaGo is not merely a brute force calculator and neither is GPT-3. They have conceptual representations. That is the advantage of deep neural networks, the ability to form concepts, as biological neural networks do.

They can form their own internal vector* representations, but they are still fixed architecture. Training AlphaGo can't change it from an RL architecture to something else, nor can training GPT-3 change it from a transformer into a more general cognitive architecture such as human brain. The datapath through a transformer is entirely prescribed. Once the weights are trained, feeding a test sample into in will indeed…

High level vector representations are concepts. That's what concepts are in the human brain too.

Re: Machine learning won't solve natural language understanding

#190

Post by HarHarVeryFunny »

namlem wrote: post #189
HarHarVeryFunny wrote: post #185

Earlier quoted context omitted.

They can form their own internal vector* representations, but they are still fixed architecture. Training AlphaGo can't change it from an RL architecture to something else, nor can training GPT-3 change it from a transformer into a more general cognitive architecture such as human brain. The datapath through a transformer is entirely prescribed. Once the weights are trained, feeding a test sample into in will indeed…

High level vector representations are concepts. That's what concepts are in the human brain too.

What about a face embedding? The vector representation is the coordinates of the face (i.e. that combination of facial features) in face-space.

I give up.

Post reply on HN