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

171–180 of 193 posts

Re: Machine learning won't solve natural language understanding

#171

Post by mcswell »

zR0x wrote: post #73
emodendroket wrote: post #14

Earlier quoted context omitted.

That's a different problem, isn't it? That's more about transcription -- getting the speech into words -- than about what he's talking about, making sense of the words once you have them.

We had to learn to collaborate before “language”. Perhaps thinking language is a key aspect of consciousness is wrong. Chomsky has said human languages themselves are just random sounds we’ve been polishing the meaning of. So yeah I have no doubt a machine can sort them correctly if we tell it to. They mean what we want and see in them. That’s hardly proving anything about consciousness. Just that a computer can sort…

"Chomsky has said human languages themselves are just random sounds we’ve been polishing the meaning of." I've read a lot of Chomsky, and I don't recall him ever saying anything like this. Can you provide a citation?

And I don't think "sorting" has anything to do with language.

Re: Machine learning won't solve natural language understanding

#172

Post by mcswell »

zR0x wrote: post #152
goatlover wrote: post #135

Earlier quoted context omitted.

Because other animals don't produce sounds which constitute abstract meaning that can be combined into sentences. Possibly a few birds and dolphins or whales might get close. But there's clearly something more going on in the brain than making sounds which contribute to word formation.

Sure there is more going on than we see on the surface. Before neuroscience and modern imaging we needed to sit and imagine and theorize. Now we don’t.

Neuroscience and brain imaging still don't tell us how language works--they're at a much to course level of granularity. Even if we could see every single neuron as it fired (which we can't), the volume of data would be overwhelming, far more than if you followed every transistor in a modern computer.

Re: Machine learning won't solve natural language understanding

#173

Post by didibus »

throwawaygh wrote: post #42
canjobear wrote: post #39

The history of NLP is littered with people claiming on theoretical grounds that XYZ is unattainable using purely statistical methods, and that some notion of the logical structure of language needs to be brought in. And yet one by one, the XYZ have been attained by statistical methods. If you think there's something NLP can't do using machine learning, make a challenge dataset. That would be much more useful than yet…

Ironically, exactly these sorts of "statistics can't..." arguments are sort of theoretically bankrupt. Either the thing you want to do is impossible or else a learned model can do it at least almost as well as... idk what the alternative even is, something not learned? Taking this to the extreme, on an example where I have first-hand experience: I would never recommend replacing your compiler passes with transformers…

I think that's a great example, the question is: can ML be as good as we are at compiling?

And then, if ML is as good as we are, and clearly we're not good enough that we had to write a systematic proof system to compile things correctly, could ML have invented this same technique and implemented that compiler correctly?

In the end, we're just back at the same place, can ML be as intelligent as we are. Is it the holy grail of AI? What are its limits?

Re: Machine learning won't solve natural language understanding

#174

Post by mcswell »

zR0x wrote: post #167
goatlover wrote: post #164

Earlier quoted context omitted.

So when you talk about emergent behavior, physical universe and biology, you're just making noise.

Yep. Babies can add and subtract when they’re days old. Can they write Shakespeare? If human language is fundamental, how is it missing from the start? Are we learning language or muscle mechanics? Why can a word or phrase mean one thing in this country and nonsense in another? If language processing has a universal basis, why all the confusing variety and ignorant ideas? 1+1=2 everywhere because we can observe the p…

"If language processing has a universal basis, why all the confusing variety..." Because the universal processing mechanism provides lots of options for individual languages--the option for different words, obviously, but the option to use or not to use morphology (and lots of varieties of morphology), and different syntax rules, etc. etc.

To use an analogy, a computer chip provides a single instruction set at the machine language level--yet you can run a huge variety of computer languages on it: FORTRAN, LISP, Python, Prolog and so forth.

Re: Machine learning won't solve natural language understanding

#175

Post by mcswell »

visarga wrote: post #2

An armchair effort to redefine the goalposts and judge NLP, but proof is in the pudding. For now, large language models are the best flavor. NLP models are already useful even in this early stage.

I don't think "Is NLP useful?" is the question they're trying to address. Hammers are useful, even in a world where there are lots of screws. NLP is useful, even in a world where there is lots of language (in English, even) that current NLP systems don't do well on.

Re: Machine learning won't solve natural language understanding

#176

Post by silent_cal »

darawk wrote: post #165
silent_cal wrote: post #162

Earlier quoted context omitted.

I think you might be missing the point. It's not that an utterance/proposition has "only one meaning", but that it is meant to represent only one concept (the speaker's) at the time it's spoken. Also, I thought that the argument about the impossibility of distinguishing between equally probable meanings (in terms of frequency in a corpus) was a good one.

> I think you might be missing the point. It's not that an utterance/proposition has "only one meaning", but that it is meant to represent only one concept (the speaker's) at the time it's spoken. While this is closer to a coherent point, i'm not sure it's particularly relevant to the idea of "natural language understanding". We consider humans to be understanding of natural language, but humans interpreting the word…

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 discoverable meaning to every intentional utterance, even if it's not always successfully understood in practice.

2. How would you go about assigning latent attributes to words?

Re: Machine learning won't solve natural language understanding

#177

Post by ZephyrBlu »

slunk wrote: post #126
ZephyrBlu wrote: post #123

Earlier quoted context omitted.

How is ML not compression? You take a training set, and you end up with a model that is smaller than the size of the training set yet performs well on it (Making the assumption the model is good here). That is compression. It has nothing to do with what the model is being used for.

> It has nothing to do with what the model is being used for. I may be misunderstanding this passage of the article, but I thought the author was claiming that machine learning (specifically training) was equivalent to compression, while language understanding is equivalent to decompression. Therefore, they can't be the same thing. Why does language understand have to be analogous to training an ML model rather than…

> Why does language understand have to be analogous to training an ML model rather than using an ML model for inference?

Why would you look at ML model inferences in particular? There is no compression or decompression going on during inferences, you're just running data through the existing weights.

Creating an ML model on the other hand is lossy compression. You reduce the size of the data (Training set -> model) in exchange for reduced accuracy (100% -> 90-95% or whatever).

NLU is decompression because you are extracting information that doesn't exist in the text.

I see ML as ahead-of-time compression (Creating a model), whereas NLU is just-in-time decompression (Extracting information from current context). Looking specifically at inference-time doesn't make sense to me because all the work for ML is done during training, not inference.

Re: Machine learning won't solve natural language understanding

#178

Post by djjdj »

qayxc wrote: post #72
nonameiguess wrote: post #41

Earlier quoted context omitted.

This seems to be misunderstanding what PAC learnable means. It's saying that for parameters epsilon and delta, you can get an algorithm for learning a hypothesis that, with probability 1 - delta, has an average error rate less than epsilon, given some number of training samples polynomial in 1/delta and 1/epsilon. This has nothing to do with the mental model. The language model doesn't have to spit out probabilities.…

There's a very important difference, though: humans can and often do qualify their interpretation. One major flaw of current PAC-based models is the inability to express certainty and being able to present the rationale behind their (lack of) confidence. One crucial aspect of human language processing is the ability to question or interrogate oneself to adjust one's interpretation. During a dialog this can be done by…

I disagree. Of course, it doesn't understand anything, it is a statistical language model. I also think that human jokes are mostly statistical in nature. That's why "Yes, but they will have to get married first" is funny. GPT was trained using texts from the Internet. It usually contains jokes and not logic predicates. At any prompt that has a structure of a joke, it will use (in the majority of the attempts) a pattern for a joke even if there is none. "If X is y, is X z?" is a typical joke pattern. If logical approach is applied in the future, it will still be derived from the statistics/reinforcement learning or something like that (the key word here is training/learning). The world is just too vast. If you want to have a resemblance of a logic model, you need a special dataset, but it will still just exploit patterns. It might be good enough, for practical use. It is arguable, if people mostly operate beyond patterns. Sorry if my text looks patronising or smth like that. I just assume.

Re: Machine learning won't solve natural language understanding

#179

Post by darawk »

silent_cal wrote: post #176
darawk wrote: post #165

Earlier quoted context omitted.

> I think you might be missing the point. It's not that an utterance/proposition has "only one meaning", but that it is meant to represent only one concept (the speaker's) at the time it's spoken. While this is closer to a coherent point, i'm not sure it's particularly relevant to the idea of "natural language understanding". We consider humans to be understanding of natural language, but humans interpreting the word…

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 form are themselves latent attributes. All modern NLP is based on this concept already. Let's look at the 'suitcase' example in the article:

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

In NLP this problem is generally called "coreference resolution". That is, resolving which prior object a given pronoun is referring to. The ambiguity of this problem is indeed very subtle, and probably quite hard for an ML algorithm to learn. You can look at a parse example here:

https://huggingface.co/coref/

This is a near state of the art coreference resolution model, and it indeed fails to properly resolve here. Although you do see that the probabilities do actually shift towards the right answer, which is (very weakly) suggestive that it might be beginning to learn it.

So, trying to unpack what's going on here linguistically, the essence of the problem is that the relation between "it" and "trophy" vs "suitcase" is contextually contingent. The necessary context is that trophies go inside of suitcases, and not vice versa. You then need to understand how the concept of insertion relates to sizes. Putting thing A inside of thing B requires that thing B be larger than thing A. This is certainly a subtle, context-rich problem.

In order to try to solve this problem, a model would need to have a more structural understanding of language. You indeed cannot learn this problem based on simple word frequency counting, for exactly the reasons they state. However, even though the frequencies of big/small may be equal, there are more nuanced conditional probabilities that are not. Conditional on the latent concept of insertion, the pattern relating object size to coreference should be very statistically apparent.

Re: Machine learning won't solve natural language understanding

#180

Post by drdeca »

visarga wrote: post #102
joe_the_user wrote: post #78

Earlier quoted context omitted.

Well, the approach of solving a corpus (advocated by GP) doesn't leave room for the possibility of asking a follow-up question so you can't train for it that way.

GPT-3 was trained on a massive text collection so it can even ask for clarifying questions if the prompt context allows for it. Why? Because there are plenty of such examples in the training data.

Sure, but this is based on something kind of like “whether someone would be likely to ask for clarification here”, not based on whether GPT3 needs clarification.

Though, I’m confident that it should be possible to make something which, when unsure, asks for clarification.

In fact, I believe something at least rather similar is already done in, uh, I think it is called “delegative reinforcement learning”, where an agent takes actions, but when it is highly uncertain, it can instead choose to have an expert (who is assumed to be competent at the task, or at least has a tolerably low risk of very bad outcomes) to step in instead.

(Or, wait, maybe delegative reinforcement learning is still just used theoretically? Not sure.)

Post reply on HN