The paper segments e-commerce queries into broad and narrow types, uses autoencoders and embeddings to handle sparsity, and shows that separate pointwise or pairwise LETOR models for each type outperform a single combined model on fashion data.
Query ambigu- ity identification based on user behavior information,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.IR 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Learning to Rank Broad and Narrow Queries in E-Commerce
The paper segments e-commerce queries into broad and narrow types, uses autoencoders and embeddings to handle sparsity, and shows that separate pointwise or pairwise LETOR models for each type outperform a single combined model on fashion data.