REVIEW 1 cited by
Deep Pairwise Learning To Rank For Search Autocomplete
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Deep Pairwise Learning To Rank For Search Autocomplete
read the original abstract
Autocomplete (a.k.a "Query Auto-Completion", "AC") suggests full queries based on a prefix typed by customer. Autocomplete has been a core feature of commercial search engine. In this paper, we propose a novel context-aware neural network based pairwise ranker (DeepPLTR) to improve AC ranking, DeepPLTR leverages contextual and behavioral features to rank queries by minimizing a pairwise loss, based on a fully-connected neural network structure. Compared to LambdaMART ranker, DeepPLTR shows +3.90% MeanReciprocalRank (MRR) lift in offline evaluation, and yielded +0.06% (p < 0.1) Gross Merchandise Value (GMV) lift in an Amazon's online A/B experiment.
Forward citations
Cited by 1 Pith paper
-
Unifying Ranking and Generation in Query Auto-Completion via Retrieval-Augmented Generation and Multi-Objective Alignment
A RAG-and-DPO trained language model that generates whole query-completion lists improved production QAC in a live test (5.44% fewer keystrokes, 3.46% more adoptions), but the offline metrics reuse the training verifiers.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.