Back

A PhD student's perspective on research in NLP in the era of LLMs

97 points10 hoursarxiv.org
dontupvoteme7 hours ago

Are papers becoming blogs?

teruakohatu7 hours ago

It has 10+ pages of references. More like a well researched lit review than a blog post with a few links.

low_tech_love6 hours ago

Yes, but putting a link to a Google Form on the abstract is a bit too much.

whatyesaid6 hours ago

It's arxiv, it's not a final version

codethief7 hours ago

I'd say the culture of scientific publishing precedes blogs by "a few" decades. There have always been papers that were blog-like in nature.

gumby3 hours ago

Consider the letters section of Phyicical Review, that turned into a weekly journal Physical Review Letters back in the 50s. It was a blog or forum back when papers were distributed on paper.

Basically because of the slow pace of review and publication the letters column became a way to talk about recent results or problems, and then follow up letters (i.e. comments on the blog posts) became common. So the editors decided to hive it off and speed up its publication schedule.

penguin_booze1 hour ago

Yeah, wait for them to be twitter threads: 1/n - where (n >> 1).

SecretDreams5 hours ago

Always have been.

vpastore5 hours ago

Only the one on arxiv. People shouldn’t take anything coming from that site seriously

maxov3 hours ago

What a strange recommendation. I do research in CS theory and machine learning and I try to find arXiv preprints when I can, they are usually more complete than conference versions of papers. If you stick to papers from authors you know or to those from well-known conferences, arXiv is often times the best source.

diffeomorphism3 hours ago

That sounds highly misleading. It is the standard preprint site in many disciplines. So you should take it as seriously as any preprint and conversely if a published article is not on the arxiv, that would be suspicious.

Frost1x5 hours ago

Eh, there are plenty of actual pre-prints you can find on arXiv. Typical flow is you find a paper of interest published elsewhere then search arXiv for the same title, authors, etc. and can even find related work. A lot of publication isn't doing much in terms of genuine peer review but formatting, catching minor errors like grammar, typo, missing references etc. arXiv is great as a legitimate source for valid information tucked behind a paywall. It's not the only option but it's one of them (checking the primary author's personal site, researchgate, or associated research institutions repositories are also there, as well as contacting the author directly).

infamouscow2 hours ago

So the math, physics, and computer science departments of every major university should be ignored? What a brain dead comment.

111010100011004 hours ago

I extend the same courtesy to this site.

dcl5 hours ago

A PhD Student's Perspective... ~20 authors.

reesul51 minutes ago

Title is off yeah, but the abstract does effectively say that the paper was written amongst a cohort of PhD students

SecretDreams5 hours ago

It takes a whole village (of uncredited MASc students) to get a PhD!

est313 hours ago

The particular headline pattern is used a lot and 99% of the time it indeed is at the front of opinion pieces written by individuals. But this time, it's different. In the syntax, in this specific form, the plural and the singular come out the same. E.g. in the sentence "I accompanied my friend to his parent's house", it can be either the house of his single mom/dad or the house of his two parents living together.

agalunar1 hour ago

Like @bdsa points out with their example, the singular and plural are actually spelled differently, viz. "parent's house" and "parents' house", despite being pronounced the same way.

https://en.wikipedia.org/wiki/English_possessive#Nouns_and_n...

bdsa2 hours ago

"I accompanied my friend to his parents' house"

rhdunn10 hours ago

I've been interested in NLP for tagging stories based on topics and themes (detectives, werewolves, murder mystery, etc.), so need accurate disambiguation of parts of speech and ways of detecting uses of metaphore, similies, etc. to describe those. I also want to be able to assess how much of the text is about a given topic, so that if I'm interested in reading a detective story from e.g. the Project Gutenberg collection, I don't want it to pick up a story where a detective is only mentioned in one paragraph.

I've looked at several existing NLP frameworks (Open NLP, Stanford NLP) and none of them are accurate enough -- they fail on things like adjectives and old english second person pronouns. This makes them practically unusable for proper sense diambiguation, lemma and part of speech based rules, etc.

The Open NLP tokenizer is also terrible at tokenizing title abbreviations ("Dr", etc.) and things like the use of "--" to delimit text, which is frequently found various Project Gutenberg texts. You can train the Open NLP tokenizer, but it works on what it has seen, so you need to give it every variation of "(Mr|Mrs|Miss|Ms|Rev|Dr|...). [A-Z]" for it to tokenize those titles; the same for other tokens.

nl7 hours ago

Have you tried Spacy?

I find it substantially better than other tools as PoS tagger.

Also worth noting the that your assertion that you need these features to classify genres isn't obviously true to me at all.

rhdunn40 minutes ago

No I haven't. Thanks for the pointer.

For detecting uses of nouns like werewolf/werewolves, or vampire/vampires, I at least need the lemma to avoid writing different cases or a regex for each noun. Likewise, lemmatization can be used to handle different spellings (e.g. vampyre, or were-wolf). Similarly for verbs.

Lemmatization works best when it is coupled with part of speech tagging, so you avoid removing the -ing in adverbs for example.

Part of speech tagging also helps avoid incorrect labeling, such as not tagging 'bit' in "a bit is a single binary value" as the verb "to bite".

That's for the simple case.

Then there are more complex cases, like generalizing "[NP] was bitten by the vampire.", where NP can be a personal pronoun (he, she, etc.) or a name. There can also be other ways to say the same thing, e.g. "The vampire bit [NP] neck." where NP is now the object form (his, her, etc.) not the subject form. With UniversalDependencies or similar style dependency relations, you could match and label sentence fragments of the form "verb=bite, nsubj=vampire, obj=NP" (like in the first sentence) and "verb=bite, nsubj:pass=NP, obj=vampire" (like in the second sentence).

Without NLP, it becomes even harder to detect split variants like "cut off his head" and "cut his head off", which are the same thing written in different ways. I want to detect things like that and label the entire fragment "beheading", including other noun phrase variants.

With more advanced NLP features -- like coreference resolution (resolving instances of he/she/etc. to the same person), and information extraction (e.g. Dracula is a vampire) -- it would be possible to tag even more sentences and sentence fragments.

viksit9 hours ago

at this point the gpt api will do all of that for you! or you can use the embeddings api and build your own systems.

rhdunn9 hours ago

The problem with GPT and other LLMs is that they don't tokenize words at a word or morpheme level, it's just blocks of up to 4 characters, so you get tokens like `!"` instead of two separate tokens. -- That makes it harder to write custom tools on top of, unlike e.g. the output/model of things like the universaldependencies project.

DougBTX9 hours ago

Do you strictly need that level of tokenisation precision to meet your high-level goals?

+1
morkalork3 hours ago
viksit9 hours ago

perhaps a spacy pipeline using gpt and huggingface?

totorovirus9 hours ago

well I see topics like NLP in ethics, healthcare, etc, which I think is a sign they don't have much to do here.

whatyesaid6 hours ago

Yeah those aren't good especially stuff like healthcare a PhD student can't get the needed data.

The other issue is, if you do focus on LLMs, it's too hyped your research would be too overlapping/competing especially as you've got a dissertation to write. It's a hard problem.

etamponi7 hours ago

Isn't the main problem with NLP research now that you'll need a ton of money to run your experiments? How can an "average" PhD researcher hope to validate their hypothesis if they need several thousand dollars per test?

nl7 hours ago

No.

There are plenty of research directions that are outlined in this document that don't require huge compute budget.

jasmer7 hours ago

Much of the interesting pure research can be done at smaller scale, the larger models are arguably more product engineering than research. At least from a certain perspective.

Randomizer427 hours ago

That is not a problem. There are literally thousands of ways to conduct any experiment at the fraction of the cost.

LoganDark5 hours ago

Thanks. Whenever I think I want to run something on a cluster of A100s, I'll just remember the thousands of ways instead, and train my LLMs that way. There's a reason why humans didn't need computers until just recently, after all. I must be so blind to not have seen this earlier.

al__be__rt2 hours ago

this paper doesn't appear to have been edited by any reputable journal, so take its authenticity at face value...

lgessler1 hour ago

I've got some bad news for you about how papers published at NLP conferences are reviewed.