Pith. sign in

Brown, Stephen A

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.CL 1

years

2019 1

verdicts

CONDITIONAL 1

representative citing papers

On Identifiability in Transformers

cs.CL · 2019-08-12 · conditional · novelty 7.0

Self-attention weights in Transformers are non-identifiable for long sequences, and the paper offers effective attention and Hidden Token Attribution as diagnostic tools.

citing papers explorer

Showing 1 of 1 citing paper.

  • On Identifiability in Transformers cs.CL · 2019-08-12 · conditional · none · ref 5

    Self-attention weights in Transformers are non-identifiable for long sequences, and the paper offers effective attention and Hidden Token Attribution as diagnostic tools.