Optimal interpolation of query embeddings from parallel translations outperforms the best monolingual query in 88/105 cases on mMARCO, showing English-driven asymmetry and negative correlation with typological distance.
and Allan, James and Carterette, Ben , title =
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
RepuLink couples endorsement and interaction networks with backward penalty/reward propagation to enforce endorser accountability and provide weighted trust initialization for new nodes.
citing papers explorer
-
When Does Mixing Help? Analyzing Query Embedding Interpolation in Multilingual Dense Retrieval
Optimal interpolation of query embeddings from parallel translations outperforms the best monolingual query in 88/105 cases on mMARCO, showing English-driven asymmetry and negative correlation with typological distance.
-
Enforcing Trust Accountability with Backward Propagation
RepuLink couples endorsement and interaction networks with backward penalty/reward propagation to enforce endorser accountability and provide weighted trust initialization for new nodes.