Search Results for author:
Found 3 papers, 0 papers with code
UniDEC : Unified Dual Encoder and Classifier Training for Extreme Multi-Label Classification
While such methods have shown empirical success, we observe two key uncharted aspects, (i) DE training typically uses only a single positive relation even for datasets which offer more, (ii) existing approaches fixate on using only OvA reduction of the multi-label problem.
Unified Generative & Dense Retrieval for Query Rewriting in Sponsored Search
To leverage the strengths of both methods, we propose CLOVER-Unity, a novel approach that unifies generative and dense retrieval methods in one single model.
NGAME: Negative Mining-aware Mini-batching for Extreme Classification
This paper identifies that memory overheads of popular negative mining techniques often force mini-batch sizes to remain small and slow training down.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
