Thank you Gabriella!

But see for yourself! concreteness.eu

All the thanks to my collaborators @gabriellavigliocco.bsky.social and @thelablab.bsky.social and big shout-out to the excellent Stanford NLU online course (this project started as my final submission).

Another bonus: these ratings can be generated "in-context", because transformer word embeddings change depending on surrounding semantic information. (Think "I go to the bank to get money" vs "I walk on the sandbank" -> previous methods were not able to differentiate btw these)

The result surpasses SOTA and even the reliability of human raters (at least in English). Interestingly, we were able to extend ratings to other languages with a simple translation step (suggesting that there may be something universal about these ratings).

Why a multimodal transformer? We know that visual information is important for accurately rating concrete words. And because emotional information is important for accurately rating abstract words, we fine-tuned our model on a dataset of emotional image descriptions.

@emollick.bsky.social you might be interested in this paper of ours! It was a very nice collab across different orgs.

I should say I mean this in a positive way for you, big fan of your work.

I think the lesson here is that most likely what you are projecting onto someone is more telling of who you are than who that person is.

also that’s such an arrogant statement.

it’s not flawed www.sciencedirect.com/science/arti...

I guess attention is all you need after all

…but true

I wish a smart mind like yours would not focus on the negative side for likes, but instead try to think about what we can do with the technology we have.

that’s personal and not to the point.

what are those other approaches and what impact have they had? I 100% appreciate the skepticism but it just works. No matter how many failures you quote it’s absolutely incredible we have a model as capable as today’s.

why always so negative, Gary?

@hugospiers.bsky.social yes it really was a great review process, can only recommend.

thanks for your support 💪