![Jordan Boyd-Graber](/img/default-banner.jpg)
- Видео 408
- Просмотров 1 216 073
Jordan Boyd-Graber
США
Добавлен 11 ноя 2006
My research lies at the intersection of natural language processing and machine learning. I post videos from my courses and research.
What’s the p(Doom)? And what’s my 5-year track record at AI Predictions?
This is a single lecture from a course. If you like the material and want more context (e.g., the lectures that came before), check out the whole course: users.umiacs.umd.edu/~jbg/teaching/CMSC_470/ (Including homeworks and reading.)
My prediction video from five (whoops, six) years ago: ruclips.net/video/BuESxqQwgmw/видео.html
Music: soundcloud.com/alvin-grissom-ii/review-and-rest
My prediction video from five (whoops, six) years ago: ruclips.net/video/BuESxqQwgmw/видео.html
Music: soundcloud.com/alvin-grissom-ii/review-and-rest
Просмотров: 95
Видео
How (Un-)Realistic is Dropout's "AI-generated" Video? [Rant]
Просмотров 27714 дней назад
This is a single lecture from a course. If you you like the material and want more context (e.g., the lectures that came before), check out the whole course: users.umiacs.umd.edu/~jbg/teaching/CMSC_470/ (Including homeworks and reading.) Breaking News: www.dropout.tv/breaking-news-no-laugh-newsroom Breaking News Example (highly NSFW): ruclips.net/video/DcX_lXP977g/видео.html Slides: docs.google...
Meta released a Diplomacy-playing LLM. How good is Cicero at talking to players? [Research Talk]
Просмотров 35821 день назад
Video presentation of our paper (More Victories, Less Cooperation: Assessing Cicero’s Diplomacy Play) presented at ACL 2024: arxiv.org/abs/2406.04643 Thanks We thank Meta for granting access to over 40,000 games played on the online platform webdiplomacy.net and for open sourcing Cicero. This commitment to open science allowed this independent reproduction of Cicero’s juggernaut abilities but a...
What Makes for a Bad Question? [Lecture]
Просмотров 2536 месяцев назад
This is a single lecture from a course. If you like the material and want more context (e.g., the lectures that came before), check out the whole course: users.umiacs.umd.edu/~jbg/teaching/CMSC_470/ (Including homeworks and reading.) What's a "Manchester" question? ruclips.net/video/9peCcstwGtU/видео.html Adversarial questions: ruclips.net/video/ipLDqWhobN8/видео.html Spiel des Wissens: www.ama...
Don’t Cheat with ChatGPT in my class! [Rant]
Просмотров 5437 месяцев назад
This is a single lecture from a course. If you you like the material and want more context (e.g., the lectures that came before), check out the whole course: users.umiacs.umd.edu/~jbg/teaching/CMSC_470/ (Including homeworks and reading.) Music: soundcloud.com/alvin-grissom-ii/review-and-rest
Is ChatGPT AI? Is it NLP? [Lecture]
Просмотров 6657 месяцев назад
This is a single lecture from a course. If you you like the material and want more context (e.g., the lectures that came before), check out the whole course: users.umiacs.umd.edu/~jbg/teaching/CMSC_470/ (Including homeworks and reading.) Music: soundcloud.com/alvin-grissom-ii/review-and-rest
What made ChatGPT Possible? [Lecture]
Просмотров 5187 месяцев назад
This is a single lecture from a course. If you you like the material and want more context (e.g., the lectures that came before), check out the whole course: users.umiacs.umd.edu/~jbg/teaching/CMSC_470/ (Including homeworks and reading.) Music: soundcloud.com/alvin-grissom-ii/review-and-rest
Are two Heads better than One also True for Large Language Models [Research]
Просмотров 2617 месяцев назад
More details: users.umiacs.umd.edu/~jbg/docs/2023_findings_more.pdf
HackAPrompt Best Theme Paper Presentation at EMNLP 2023 [Research]
Просмотров 3387 месяцев назад
Read the paper: umiacs.umd.edu/~jbg/docs/2023_emnlp_hackaprompt.pdf Project webpage: paper.hackaprompt.com/
What Makes for a Good Video Presentation: The Best ACL 2023 Videos
Просмотров 7737 месяцев назад
Full list of the 2023 ACL Best Papers Here: 2023.aclweb.org/program/best_papers/ 6:21 - When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memories Alex Mallen, Akari Asai, Victor Zhong, Rajarshi Das, Daniel Khashabi, and Hannaneh Hajishirzi 12:07 - KILM: Knowledge Injection into Encoder-Decoder Language Models Yan Xu, Mahdi Namazifar, Devamanyu Haza...
How would you feel if this video's title didn't match what it's about? [Research]
Просмотров 1999 месяцев назад
Full paper: arxiv.org/pdf/2310.13859.pdf
Helping Computers add "A Little Extra" when they Translate [Research]
Просмотров 1839 месяцев назад
Research talk for our paper: Automatic Explicitation to Bridge the Background Knowledge Gap in Translation and its Evaluation with Multilingual QA arxiv.org/pdf/2312.01308.pdf Presented at EMNLP 2023
How is a good Question is like an NP-Complete Problem? [Lecture]
Просмотров 1809 месяцев назад
This is a single lecture from a course. If you you like the material and want more context (e.g., the lectures that came before), check out the whole course: umiacs.umd.edu/~jbg/teaching/CMSC_848/ (Including homeworks and reading.) Music: soundcloud.com/alvin-grissom-ii/review-and-rest
How can Trivia Games around the World improve AI? [Lecture]
Просмотров 1839 месяцев назад
This is a single lecture from a course. If you you like the material and want more context (e.g., the lectures that came before), check out the whole course: umiacs.umd.edu/~jbg/teaching/CMSC_848/ (Including homeworks and reading.) Manchester Paradigm: ruclips.net/video/JcNpiD4odT0/видео.html ABC Dataset: www.nlp.ecei.tohoku.ac.jp/projects/jaqket/ ABC Competition: abc-dive.com/portal/ Mancheste...
QA is not one size fits all: Getting different answers to the same question from an AI [Lecture]
Просмотров 16910 месяцев назад
QA is not one size fits all: Getting different answers to the same question from an AI [Lecture]
My video making process (what not to do) [Lecture]
Просмотров 15511 месяцев назад
My video making process (what not to do) [Lecture]
Natural Questions: Google's QA Dataset Five Years Later and Why it's Impossible Today [Lecture]
Просмотров 26011 месяцев назад
Natural Questions: Google's QA Dataset Five Years Later and Why it's Impossible Today [Lecture]
The Fulfilling Straight Line Mission (from a Computer Science Perspective) [Rant]
Просмотров 21411 месяцев назад
The Fulfilling Straight Line Mission (from a Computer Science Perspective) [Rant]
Update: Why you should call Large Language Models Muppet Models [Rant]
Просмотров 88611 месяцев назад
Update: Why you should call Large Language Models Muppet Models [Rant]
Academic Conferences' Dark Secret and Why Virtual Conferences will never Improve [Rant]
Просмотров 239Год назад
Academic Conferences' Dark Secret and Why Virtual Conferences will never Improve [Rant]
How to Know if Your Language is Broken [Rant]
Просмотров 207Год назад
How to Know if Your Language is Broken [Rant]
What I expect from TAs in my Course [Lecture]
Просмотров 288Год назад
What I expect from TAs in my Course [Lecture]
Recurrent Neural Networks as Language Models and the two Tricks that Made them Work [Lecture]
Просмотров 1,5 тыс.Год назад
Recurrent Neural Networks as Language Models and the two Tricks that Made them Work [Lecture]
Explaining Recurrent Neural Networks through a silly Word-Counting Sentiment Example [Lecture]
Просмотров 783Год назад
Explaining Recurrent Neural Networks through a silly Word-Counting Sentiment Example [Lecture]
What general term should you use for models like BERT and GPT? [Rant]
Просмотров 1,5 тыс.Год назад
What general term should you use for models like BERT and GPT? [Rant]
No, CICERO has not "mastered" Diplomacy [Rant]
Просмотров 1,3 тыс.Год назад
No, CICERO has not "mastered" Diplomacy [Rant]
Can ChatGPT and You.com answer questions I thought no AI can answer? [Rant]
Просмотров 1,1 тыс.Год назад
Can ChatGPT and You.com answer questions I thought no AI can answer? [Rant]
How to read my course webpage [Lecture]
Просмотров 523Год назад
How to read my course webpage [Lecture]
Why I Teach Using a Flipped Classroom and How it Works [Lecture]
Просмотров 446Год назад
Why I Teach Using a Flipped Classroom and How it Works [Lecture]
Amazing!
Amazing!
You realise this is a comedy show, right? It's not supposed to be taken this seriously.
Dropout literally has a whole show about nerds making pedantic corrections called "Um, Actually". Mike Trapp was the host. But I realize I don't get any points because I failed to say "Um, Actually".
And if this is a way for new people to understand AI better than Grant does, I consider that a win.
Repost, first post was missing a final edit, sorry about that!
This guy is good, great explanation!
Very interesting, thanks for sharing
Great to see a breakdown of what Cicero is and is not.
Great video, thank you 👏👏
Beautiful !!
I absolutely agree. Tossing more layers just *feels* wrong. There definitely is something missing in these newer neural models that while they perform well, they don't really do so efficiently. Either they in the future will massively improve via using some of the old techniques, or by being crafted architecturally with more biological inspiration.
Can you please reference the paper you mentioned form google?
got it in the description.
🎉
Masterpiece! Amazing intro, thanks
As much as I hate LLMs... do LLMs use Chinese Restaurant Processes and/or Kneser-Ney?
Not really, this is older technology to relate similar contexts together. Modern LLMs (or Muppet Models, as I like to call them) use continuous representations to do that.
Perfect! Thank you so much.
Thanks, that was informative. Learned something.
I haven't finished the video, so apologies if you cover it, but in the 2023 CS224N NLP lecture on coreference resolution, Chris Manning introduces the (very complicated and demoralizing, to me) Hobb's algorithm, and then basically says something like "Hobbs HIMSELF said publicly that he didn't like the algorithm, and often pointed to it as ~an example of how we clearly needed something better."
Synthetic data generations has become so easy now thanks to LLM!
Your video has sparked a meaningful conversation. How has being a young-onset Parkinson's patient shaped Jessica's perspective on life? As the host of a dream interpretation channel, I'm curious to explore how her experiences with Parkinson's influence her dreams and subconscious mind. I truly appreciate the opportunity to learn more about Jessica's journey, and I've already liked and subscribed to the channel for more insightful content like this.
13:11 there is mistake in last line t(e1,f2) * ( t(e2,f0) + t(e2,f1) + t(e2,f2) ) should be this slides duplicate f2
Jordan is soooooooo cool ...🤭 I really want to meet you at the NLP conference ...!!!!
Can you share this video with the president of Harvard? I don’t think she got the message. Yet somehow DEI still think it was okay for her to cheat. DEI is accusing everyone of racism.
Awesome, can't believe guys tried doing this in your class. This is like commiting a burglary and leaving a confession note and a business card. This is really funny.
Not just that. I'm not sure what the right analogy is, but it's that *plus*: trying to rob the safe company, the thief's guild, or the police station.
thanks for using my slides! :)
Thanks for making such great slides!
My book mentioned about continuous and discrete data, but they did not explain anything. Your video clarified it so well for me Thanks a lot!!!
You're welcome! Glad to be of help. This is an old video (pre-neural revolution), I just went through it again and it holds up pretty well (except for my not-so-great green screen).
Fire video after fire video with this guy. Incredible.
If you're a human, thank you! If you're a bot, you're an excellent example of the technology in the video, so thank you for providing a real-world example. :)
Great intro video, and lovely coverage of the key concepts there. I listened to the guy credited with coming up with the transformer model, and I think in adjusting the word vectors to predict the next word in a sequence more effectively, its also mapping phrases, sentences, ideas and concepts into multidimensional space, up to its input context length. So it ends up having what Isaac Asimov described as a "perceptual schematic" of the world, how everything relates to everything else, encoded in multidimensional space. Then all the behaviours it's trained to perform based on rlhf are possible because it has this initial perceptual schematic.
Yes, but that schematic isn't a schematic (yet). It's just a vector space, which means that the exact meanings can get fuzzy. This association can only get us so far, which is why we're starting to see the technology's limits. Exciting to see what happens!
@JordanBoydGraber I'm not sure we are starting to see the technology's limits? I appreciate your breadth and depth of knowledge in the field, but all of the indications from these companies would appear to suggest that we're not close to approaching an asymptote with regards to these models yet. I do think I know what you're saying though, and I agree, what it has is a set of interrelated numbers, it has no actual "knowledge" per se, its what it's trained to do with these interrelated numbers really. I think the best analogy to get at what im saying is with the vision transformer model. It starts off representing small patches of the image as vectors like words, and has an associated positional encoding vector for each patch too. It learns to not only classify the entire image, and to cluster similar images in dimensional space when it classifies them, but it also learns positional encodings for each patch of the image, adjusting the positional encodings for each patch of the image, to orient it correctly in terms of the image so it has a much better chance of classifying the whole image. I see the same with the language transformer model. It's adjusting vectors on a word level, but because it's using these word vectors to do something with the whole block of text, its still learning to place the entire block of text, in one word iterations, up to its context length, in certain positions in interrelated dimensional space, just like it does with images, even though it only has vectors for words, like it only has vectors for small image patches. Then further training helps it prune down this vast interrelation to a conceptual map (2nd part just a theory from me here). I think there may be a limit with purely language based models, but potentially the sky is the limit with multimodality. The constraining factor appears to be hardware ATM imo.
This is an amazing video. Very intuitive. Thank you.
Incredible work. Sharing with my class.
This was very helpful tyvm!
9:42 for Rm(H), what is the use of taking expectation over all samples? As we saw previously, like from 6:12, calculation of empirical Rademacher does not use the true label of samples, rather just the size of the sample.
Interesting
It's really wonderful when no nonsense science communication comes with a generous helping of low-key courage. Dope.
Really excellent like the other videos on this series. I am sharing the course with colleagues and hoping to go thru the syllabus in the Spring. Thank you for the excellent work, Prof!
Excellent
This is incredible. Thanks!
in 6:55, it is said that H(x, M) = sum(log(M(xi))), but accroading to the defination of cross entropy, it should be H(P, Q) = sum(-1 *P(x)log(Q(x))), so are we assuming P(x) is always one when computing perplexity?
This is a really good point. Typically when you evaluate perplexity you have one document that somebody actually wrote. E.g., you're computing the perplexity of the lyrics of "ETA". In that case we have a particular sequence of words. Given the prefix "He's been totally", the probability of P(x_t) = "lying" and everything else is zero. For some generative AI applications, this might not be true. E.g., for maching translation you might have multiple references. Thanks for catching this unstated assumption!
Excellent interview. Excellent YT Channel, thank you!
That's just a brilliant video, I appreciate the fact that your videos always introduce an uncommon point of view that still makes a lot of sense.
IS there a link to the "mark riddle(?)" transformer diagram? can't find it in the description.
pbs.twimg.com/media/FZUiCbpXgAEd11j?format=jpg&name=large ,say no more ;)
Amazing video!! I’m so glad you covered this. Your passion and enjoyment about the subject really comes through. Thanks so much for this ☺️
should equation 6) be: 2e^(-epsilon*m/2)? This is because the chance of sampling from the whole highlighted region is epsilon, so the probability of sampling from a specific region is epsilon/2? Thank you for the great lecture!
Yes I think so too, epsilon/2 for each side
Cool idea! Other rating ideas: how evenly does the straight line cut the country into two pieces? Are they the same size? Same Population each side of the line? This way you can allow for easy countries and hard countries, where you can score the "even" disection of countries irrespective of how long the line is. Also a hint: your microphone has some awful automatic gain setting or something, where all the quiet sounds are amplified and all the loud sounds are quieted down, so your tiniest breathing in is the same volume as your loudest talking bits. It's really annoying
1) I like the population bisection idea. It's obviously easier to go through less popular areas. 2) Thanks for mentioning that, it's easy to tune these sorts of things out.
Loved this video 😅 for some reason ❤
Thanks! Good to know. Perhaps I'll do more things like this. Not relevant to any of my classes, really, but I enjoyed doing it.
the name muppet models is super cute but alas the perspective that muppet models just make stuff up is misplaced, true in some ways but also dangerously wrong, they do get things wrong or out of place when speaking off the top of their head, but, um, statistically far less than humans do already, the confusion is that they're so much better at talking than humans that they can give almost accurate coherent essays about stuff completely off the top of their heads while a human would just be saying "uhhhhh", if you give them the equivalent of a human salary worth of compute they can also check the accuracy of things a zillion times better than any human could ever check
Dance your cares away <clap><clap> Worries for another day <clap><clap>
Sing und schwing das Bein, <klatschen> lass die Sorgen Sorgen sein.
It's canon now.
You don't have enough views.
From your mouth to the algorithm's parameters!
Yuval Pinter makes the excellent point that I shouldn't conflate "writing system" and "language". Indeed, this video should have been titled "How to Know if Your Writing System is Broken". See more in their excellent position paper on the subject: aclanthology.org/2023.cawl-1.1/
Lol what was that short powermark on question 32