Agreed. In the 2000s it was all about BM25 in the NLP community. I hardly see any paper that did not mention it in my opinion.

For sure, it’s very popular, just not the best anymore (and actually far from it).

And dependency chaining. But yes, lots of BM25.

The 2000s and even 2010s was a wonderful and fairly theoretical time for linguistics and NLP. A time when NLP seemed to harbor real anonymized general information to make the right decisions with, without impinging on privacy.

Oh to go back.