Show HN: Natural Language Processing Demystified (Part One) • Hacker News Board

Re: Show HN: Natural Language Processing Demystified (Part One)

#41

Post by jasfi » Thu, May 19, 2022, 4:48 AM UTC

Der_Einzige wrote: post #34

jasfi wrote: post #13

I'm working on extracting facts from sentences, see https://lxagi.com . Which are the toughest NLP problems you know of that aren't being solved satisfactorily?

Queryable, word level, extractive summarization with grammatical correctness. AKA: what a human does when they are "highlighting" a document. think extractive QA but the answer size should be configurable and the answer can potentially be multiple spans, and spans may not need to be contiguous. If you got a solution, I'd love to see it - and you could even beat the baselines for the only dataset that exists for it: h…

Thanks, I'll add that to the list of possible use cases, although that will take additional time. The solution won't be ready anytime soon, so please sign-up for the announcement list on the website if you're interested.

Re: Show HN: Natural Language Processing Demystified (Part One)

#42

Post by ad404b8a372f2b9 » Thu, May 19, 2022, 12:09 PM UTC

jll29 wrote: post #3

NLP researcher here. It's great to see many offerings for courses and tutorials, and NLP has made a lot of progress, in terms of both its science as well as its re-usable software artifacts (ibraries & notebooks, standalone tools). But what saddens me is too many people are trying to dive into NLP without trying to understand language & linguistics first. For example, you can run a part of speech (POS) tagger in thre…

"Every time I fire a linguist, the performance of the speech recognizer goes up"

- Frederick Jelinek

Re: Show HN: Natural Language Processing Demystified (Part One)

#43

Post by adamsmith143 » Thu, May 19, 2022, 2:32 PM UTC

amitport wrote: post #26

adamsmith143 wrote: post #23

Earlier quoted context omitted.

I'm not at all sympathetic to this viewpoint. The Deep Learning revolution has shown us time and time again that Deep Learning experts universally outperform SME on modelling performance. I an almost 100% certain that the teams building big Transformers which are now by far the best NLP models (OpenAI, Meta, Google Brain, Deepmind, etc) are not made up of linguistic experts but Deep Learning experts.

These groups are not mutually exclusive.

Maybe not but I'd guess that in this context the marginal gain for learning more about Linguistics is going to be dwarfed by learning more about Deep Learning.

Re: Show HN: Natural Language Processing Demystified (Part One)

#44

Post by jasfi » Thu, May 19, 2022, 3:46 PM UTC

Der_Einzige wrote: post #34

jasfi wrote: post #13

I'm working on extracting facts from sentences, see https://lxagi.com . Which are the toughest NLP problems you know of that aren't being solved satisfactorily?

Queryable, word level, extractive summarization with grammatical correctness. AKA: what a human does when they are "highlighting" a document. think extractive QA but the answer size should be configurable and the answer can potentially be multiple spans, and spans may not need to be contiguous. If you got a solution, I'd love to see it - and you could even beat the baselines for the only dataset that exists for it: h…

Can I ask more about your interest in NLP? How can I contact you?

Re: Show HN: Natural Language Processing Demystified (Part One)

#45

Post by true_religion » Sat, May 21, 2022, 7:16 AM UTC

jll29 wrote: post #3

NLP researcher here. It's great to see many offerings for courses and tutorials, and NLP has made a lot of progress, in terms of both its science as well as its re-usable software artifacts (ibraries & notebooks, standalone tools). But what saddens me is too many people are trying to dive into NLP without trying to understand language & linguistics first. For example, you can run a part of speech (POS) tagger in thre…

I don’t know if anyone wants to dive into NLP as much as they just want to solve their problem at hand.

You are right that lack of fundamental knowledge is problematic, especially that tools can allow you to make a greater quantity of solutions and therefore also a greater quantity of mistakes.

However, at least the problem is still being solved.

For example, a few months ago I wanted to organize my media collection by tagging files with artist names. I had a list of artist names but it wasn’t comprehensive so I wired together a bunch of python NLP libraries together to automatically pull out proper nouns from filenames, recognize English names, then annotate the files.

I know almost nothing about parts of speech or anything else, so I made mistakes. About 10% of the results were errors in the first run, but after tuning it was down to about 1% which was good enough to run over the entire media library.

If not for the tools, I would have never been able to finish that chore in a single day. To me, it was worth it despite my amateur mistakes.

I view the library just like any other tool: a screw driver, a hammer, a wrench. I’m not a plumber or a carpenter, or an NLP researcher but I still want to use tools to fix my leaky faucets, remount my leaning cabinet doors, and organize my media collections as weekend projects.