This interactive visualization displays 21 million scientific papers collected in the PubMed database, maintained by the United States National Library of Medicine and encompassing all biomedical and life science fields of research.
You can scroll the narration in the left part of the screen, and interact with the visualization in the right part of the screen. Zooming in loads additional papers. Information about each individual paper appears on mouse-over, and clicking on a paper opens its PubMed page in a separate window. Search over titles is available in the upper-right corner.
Explanatory overview thread here
Why transformers are obviously good models of language
- Nobody knows how language works, but many theories abound. Transformers are a class of neural network that process language automatically with more success than alternatives, both those based on neural computations and those that rely on other (e.g. more symbolic) mechanisms. Here, I highlight direct connections between the transformer architecture and certain theoretical perspectives on language. The empirical success of transformers relative to alternative models provides circumstantial evidence that the linguistic approaches that transformers embody should be, at least, evaluated with greater scrutiny by the linguistics community and, at best, considered to be the currently best available theories.