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

Advanced NLP with SpaCy

course.spacy.io

Post reply on HN
Print view View original

31–40 of 60 posts

Re: Advanced NLP with SpaCy

#31

Post by jakderrida »

pharmakom wrote: post #12
tomohelix wrote: post #3

No offense, but isn't the NLP field effectively solved with the creation of LLMs, or at least for the majority of the tasks you would expect from an NLP application? I am sure you can find some special areas or niches where traditional NLP approaches would outcompete a black box like LLMs. But with the LLMs becoming much more efficient now after quantization to the point you can run them locally, I think there is a g…

We still use regex despite there being LLMs that can approximate this functionality They have different trade offs in the solution space. I have no doubt that prompt engineering will eat into a bunch of work that was previously done using NLP though - particularly for prototyping.

Quite honestly, I'd imagine getting LLMs to generate regex solutions seems most feasible. Regex can basically run through a character vector full of millions in impressive time. Plugging all of them into an LLM and awaiting a response taking 20 seconds each might be impractical for most use cases. However, asking an LLM to pack the regex statement full of synonyms and | operators just might seem a better solution. Especially if you can give the LLM some samples of what you're looking for.

Re: Advanced NLP with SpaCy

#32

Post by jakderrida »

markisus wrote: post #28
gattilorenz wrote: post #9

Earlier quoted context omitted.

I don’t understand what it means to be “solved”. It’s like saying that “architecture is now solved”, “physics is solved”, or “programming is solved”. It’s a field of science and/or engineering, it’s not like we will ever run out of things to try/build/investigate. LLMs work… to a certain extent, with limitations and tradeoffs, and for some things. Would you spend days, money and Co2 to split a huge text corpus in sen…

I take it to mean that there is an effective generally accepted solution or methodology for problems in the field. Bridge building has been largely solved by methods of mathematical and computational structural analysis, manufacturing, and government regulation. We know how to build a bridge. Before the solution was known, designers would just go by intuition and we wouldn’t have any actual assurance that the bridge…

But your bridge building analogy doesn't define what "solved" means still. When it comes to bridge building, "solved" means the bridge won't collapse under expected conditions. All you did was bring up an area where "solved" does have a definition, but that does nothing to define "solved" in the field we're discussing.

Re: Advanced NLP with SpaCy

#33

Post by jakderrida »

politelemon wrote: post #4
tomohelix wrote: post #3

No offense, but isn't the NLP field effectively solved with the creation of LLMs, or at least for the majority of the tasks you would expect from an NLP application? I am sure you can find some special areas or niches where traditional NLP approaches would outcompete a black box like LLMs. But with the LLMs becoming much more efficient now after quantization to the point you can run them locally, I think there is a g…

At least for those of us unfamiliar with the field, LLMs are an easy way of getting the task done. The only thing worth noting I suppose is that the most effective ones are behind paywalls. In some cases though you may want the NLP task to be run locally - you want it to be free, and should not require excessive resources - for those cases libraries like Spacy and NLTK make sense. Yes there are projects like llama.cp…

>At least for those of us unfamiliar with the field, LLMs are an easy way of getting the task done.

This is actually an excellent point. You don't really need to know, or even give a damn, how LLMs work in order to make use of them. Find me a C++ library where I can be 100% clueless as to what it does while also integrating it into my code.

Re: Advanced NLP with SpaCy

#34

Post by hzay »

tomohelix wrote: post #3

No offense, but isn't the NLP field effectively solved with the creation of LLMs, or at least for the majority of the tasks you would expect from an NLP application? I am sure you can find some special areas or niches where traditional NLP approaches would outcompete a black box like LLMs. But with the LLMs becoming much more efficient now after quantization to the point you can run them locally, I think there is a g…

Regression is unsolved, for a start. Re LLMs, they are expensive to finetune and their inference times & memory footprints are poor compared to smaller models.

Re: Advanced NLP with SpaCy

#35

Post by bob1029 »

tomohelix wrote: post #3

No offense, but isn't the NLP field effectively solved with the creation of LLMs, or at least for the majority of the tasks you would expect from an NLP application? I am sure you can find some special areas or niches where traditional NLP approaches would outcompete a black box like LLMs. But with the LLMs becoming much more efficient now after quantization to the point you can run them locally, I think there is a g…

The #1 thing for me right now is determinism and traceability. I am in a "serious" business domain and non-determinism is a big no-no. We have to be able to justify everything in a traditional sense at the end of the day. Explaining to a regulator that we declined a customer as a consequence of a vast, unthinkable sea of weights and biases is not going to fly.

For each predicted output token, I want to know exactly which source document(s) were utilized including indices from those documents and relevant statistics.

Re: Advanced NLP with SpaCy

#36

Post by Al-Khwarizmi »

tomohelix wrote: post #3

No offense, but isn't the NLP field effectively solved with the creation of LLMs, or at least for the majority of the tasks you would expect from an NLP application? I am sure you can find some special areas or niches where traditional NLP approaches would outcompete a black box like LLMs. But with the LLMs becoming much more efficient now after quantization to the point you can run them locally, I think there is a g…

This is a common opinion, but when I speak to small companies that want to use NLP (e.g. in the medical domain) and I give an account of the advantages and disadvantages of "classic" NLP vs. generative LLMs for information extraction applications, they tend to prefer classic NLP more often than not.

The possibility of models making things up combined with zero explainability, together with high costs (or using third-party services and having to upload sensitive data who knows where) are red flags for many.

This may change in a few years if the weaknesses of generative LLMs are successfully addressed, but for the moment I think "classic" NLP still has its place.

Re: Advanced NLP with SpaCy

#37

Post by axpy906 »

roenxi wrote: post #8
tomohelix wrote: post #3

No offense, but isn't the NLP field effectively solved with the creation of LLMs, or at least for the majority of the tasks you would expect from an NLP application? I am sure you can find some special areas or niches where traditional NLP approaches would outcompete a black box like LLMs. But with the LLMs becoming much more efficient now after quantization to the point you can run them locally, I think there is a g…

1) It is extremely rare for a field to ever 'be solved'. There is still active research into how to multiply 2 numbers together. NLP is not anywhere close to solved. 2) LLMs have different trade-offs to fundamental techniques. Linear regression still gets lots of use despite there usually being a theoretically better method for any specific application. There will be parallels to that in NLP. 3) Isn't the article tal…

Large Language Model in my opinion means that it has billions of parameters and possibly cannot fit on a single machine.

Not sure what Spacy is doing under the hood these days but always thought of “neural net” as word2vec type model which won’t hit the above definition.

Re: Advanced NLP with SpaCy

#38

Post by esafak »

syllogism wrote: post #19
tomohelix wrote: post #3

No offense, but isn't the NLP field effectively solved with the creation of LLMs, or at least for the majority of the tasks you would expect from an NLP application? I am sure you can find some special areas or niches where traditional NLP approaches would outcompete a black box like LLMs. But with the LLMs becoming much more efficient now after quantization to the point you can run them locally, I think there is a g…

(Original author of spaCy and Explosion CTO here) Okay so, first some terminology. LLMs can mean a bunch of different things, people call models the size of BERT LLMs sometimes. So let's talk specifically about in-context learning (ICL) with either zero or a few examples. So we'll say LLM ICL, and contrast that with techniques where you annotate enough data to train with, which might only be something like 10-40 hour…

At the same time, I expect the industry to consolidate NLP on LLMs. Standardization has benefits, and compute only gets cheaper.

Re: Advanced NLP with SpaCy

#39

Post by croes »

yorwba wrote: post #20
rhdunn wrote: post #16

Earlier quoted context omitted.

LLMs are useful for things like predicting/generating text, and summarizing text. They are not useful if you want to do other NLP tasks that include things like: 1. Identifying (and highlighting/extracting) the language that spans of text are in within a different language (e.g. a French phrase in English). 2. Text search and highlighting, where you need to do things like performing word stemming or lemmatization on…

1. Prompt: """ The following English text contains several French phrases. List all of them. Text: Gabonese President Ali Bongo Odimba was deposed in a coup d'etat spearheaded by his father's former aide-de-camp Brice Oligui Nguema, shortly after the announcement that Bongo had won the 2023 election. List of French phrases from the text: - """ Response: """ coup d'etat - aide-de-camp """ 2. Prompt: """ Turn all words…

LLMs is non deterministic, so tomorrow the same prompt can give you a totally different result.

That's what renders it nearly useless for such tasks, because you always have to check everything.

Re: Advanced NLP with SpaCy

#40

Post by yorwba »

croes wrote: post #39
yorwba wrote: post #20

Earlier quoted context omitted.

1. Prompt: """ The following English text contains several French phrases. List all of them. Text: Gabonese President Ali Bongo Odimba was deposed in a coup d'etat spearheaded by his father's former aide-de-camp Brice Oligui Nguema, shortly after the announcement that Bongo had won the 2023 election. List of French phrases from the text: - """ Response: """ coup d'etat - aide-de-camp """ 2. Prompt: """ Turn all words…

LLMs is non deterministic, so tomorrow the same prompt can give you a totally different result. That's what renders it nearly useless for such tasks, because you always have to check everything.

There's nothing about LLMs that is inherently nondeterministic. Sure, if you're using some API you have no control over, anything could happen. But if you run it on your own hardware, you can make it as deterministic as any classic NLP approach.

And whether you always have to check everything is a separate question from nondeterminism. You could have a deterministic heuristic that is often wrong in a domain where mistakes are fatal, or you could have a nondeterministic model that is almost always correct for a task where errors cost next to nothing.

Post reply on HN