A two-level self-attention encoder (Multiresolution Transformer Network) predicts the next query in a search session and beats recurrent baselines on AOL and OnlineX logs.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Multiresolution Transformer Networks: Recurrence is Not Essential for Modeling Hierarchical Structure
A two-level self-attention encoder (Multiresolution Transformer Network) predicts the next query in a search session and beats recurrent baselines on AOL and OnlineX logs.