Rada Mihalcea: Looking back at the work we’ve done ...| Robocrunch AI

Looking back at the work we’ve done back in 2006 on measuring text semantic similarity, it would be fair to say “this is obvious” — and surprisingly it feels good to have done work that in retrospect appears as “obvious” ✨ https://t.co/BQ1wqgG3KP
— Rada Mihalcea (@radamihalcea) May 4, 2022

https://cse.engin.umich.edu/stories/paper-recognized-for-lasting-impact-on-natural-language-processing

🌟🎉Special congratulations to Prof. @radamihalcea, her 2006 paper “Corpus-based and Knowledge-based Measures of Text Semantic Similarity” was r ...

Shared by MichiganAI at 5/11/2022 1-1

Throw in the facts that a) when we encounter language we can't help but imagine a mind behind it and b) today's pattern recognizers are good at ...

Shared by Emily M. Bender at 5/17/2022 0-5

https://arxiv.org/abs/2102.03406

In the same spirit, I enjoyed reading the perspective from @santoroAI et al https://t.co/FQtcaxVlCy We should aim for functional equivalence, d ...

Shared by Animesh Garg at 3/11/2022 2-2

We discuss (weak) equivalence in syntactic theory and point out that it "can only be understood as relative to a particular collection of phenom ...

Shared by Adina Williams at 3/9/2022 0-3

I'm amused: @semanticscholar has wrongly attributed two recent under-review papers to me on a topic that I have not worked on before but that I ...

Shared by Christopher Potts at 5/5/2022 0-9

https://aclanthology.org/2020.conll-1.45/

Also check out earlier work that also investigated term frequencies on symbolic tasks: Are Pretrained Language Models Symbolic Reasoners Over K ...

Shared by Alex Tamkin at 2/19/2022 0-4

768