43 citations · 106 across the 27 of their papers we have counts for
Showing 2019Show all
2 papers · 1 filter
cs.LG2019★ 1 cited
Multiscale Self Attentive Convolutions for Vision and Language Modeling
Oren Barkan
Self attention mechanisms have become a key building block in many state-of-the-art language understanding models. In this paper, we show that the self attention operator can be fo…
cs.LG2019
Scalable Attentive Sentence-Pair Modeling via Distilled Sentence Embedding
Oren Barkan, Noam Razin, Itzik Malkiel +3
Recent state-of-the-art natural language understanding models, such as BERT and XLNet, score a pair of sentences (A and B) using multiple cross-attention operations - a process in…