Rendered at 21:40:05 GMT+0000 (Coordinated Universal Time) with Cloudflare Workers.
samrus 4 hours ago [-]
Deserved. word2vec is a beautiful peice of science. The hypothesis behind it was so amazing. I kinda feel like everything else in LLMs (including the attention mechanism itself) is just engineering around the representation learning breakthrough that word2vec demonstrated
jacquesm 3 hours ago [-]
And with applications far outside the original scope, which I think is one of the hallmarks of foundational discoveries. As soon as you have that one puzzle piece a whole lot of other stuff comes into focus.
vatsachak 4 hours ago [-]
I remember being presented Word2Vec as an undergrad in 2016 and I could not predict the sci-fi reality that is today
__atx__ 2 hours ago [-]
Indeed. I remember taking a machine learning course as an undergrad in 2018 and scratching my head how could systems like these possibly scale to meaningfully interacting with computers let alone the real world. Well, here we are :)
resters 4 hours ago [-]
The idea that a word is defined by the company it keeps was decades old. Mikolov’s insight was that you could learn it at scale with a very simple model, and that meaning would fall out as geometry. Obvious in hindsight, foundational in practice.
microtonal 2 hours ago [-]
Not to downplay his accomplishments (I have sung my praises in another comment), but even vector models were already around and somewhat popular before. Much of it started in Information Retrieval with things like TF-IDF vectors and later PPMI matrices that were converted to small, dense matrices with SVD. Of course, later Yoshua Bengio et al. introduced neural language models for training embeddings.
There is even a paper by Levy & Goldberg from 2014 that shows that skip-gram with negative sampling implicitly factorizes a PPMI word-context matrix.
But Mikolov's formulation is very nice in that it is a simple linear model that allows for a very simple Hogwild optimization that worked very well/fast on multi-core CPUs of the time.
DC-3 2 hours ago [-]
Just FYI: You sang his praises. If you "sang my praises", that means you celebrated yourself.
microtonal 3 hours ago [-]
Well-deserved. Even though more complex language models won in the end, his stripping down of word embedding training from RNNs/convolution models to a simple linear model was the thing that was needed for compute at the time and completely dominated the field for five years or so. I do miss the times a little where you could train a cutting-edge model with a reasonable CPU (for training embeddings with word2vec) and a single GPU (some BiLSTM or transformers before BERT).
If I remember correctly, I read somewhere he initially had a hard time getting the word2vec paper accepted at a conference.
BOOSTERHIDROGEN 4 hours ago [-]
I still in awe how could someone understand well in math, is it pure nature or nurture. Could any average possible to grasp the beauty of math, starting from high school level math understanding.
_false 3 hours ago [-]
This is my first time hearing about Tomas in a while. Does anyone know what he has been up to since word2vec?
armcat 2 hours ago [-]
His team is doing amazing work in making open weight models even better. Chinese models are notorious for their thinking verbosity and tenacity to call tools repeatedly [1] so his team is making them more efficient and on-point [2].
There is even a paper by Levy & Goldberg from 2014 that shows that skip-gram with negative sampling implicitly factorizes a PPMI word-context matrix.
But Mikolov's formulation is very nice in that it is a simple linear model that allows for a very simple Hogwild optimization that worked very well/fast on multi-core CPUs of the time.
If I remember correctly, I read somewhere he initially had a hard time getting the word2vec paper accepted at a conference.
[1] https://armincat.com/articles/ai-agent-executed-same-query-2...
[2] https://bottlecapai.com/post/thinkingcap-qwen3-8-flash-next/