Yuchen Liang

Although our paper on fruit fly inspired neural architectures for NLP has already been discussed on twitter, I want to cast a bit more technical light on it. #ICLR2021 Can a Fruit Fly Learn Word Embeddings❓ Paper: arxiv.org/abs/2101.06887 Demo: flyvec.org 🧵1/N

Can a Fruit Fly Learn Word Embeddings? FlyVec: interactive tool for exploring concepts learned by individual neurons and their activity in response to query sentences Demo flyvec.org Paper arxiv.org/abs/2101.06887 With @YuchenLiangRPI @DimaKrotov #NLProc #ICLR2021

Work done by @YuchenLiangRPI @wrong_whp @Ben_Hoov @LeopoldGrinberg @navlakha_lab @mj_zaki @DimaKrotov

We show that not only can the fruit fly network motif achieve performance comparable to existing methods in NLP, but, additionally, it uses only a fraction of the computational resources (shorter training time and smaller memory footprint).

In our #ICLR2021 paper we study a well-established neurobiological network motif from the fruit fly brain and investigate the possibility of reusing its architecture for solving common natural language processing tasks. Paper: arxiv.org/abs/2101.06887