Atomized Search Length: Beyond User Models
We argue that current IR metrics, modeled on optimizing user experience, measure too narrow a portion of the IR space. If IR systems are weak, these metrics undersample or completely filter out the deeper documents that need improvement. If IR systems are relatively strong, these metrics undersample deeper relevant documents that could underpin even stronger IR systems, ones that could present content from tens or hundreds of relevant documents in a user-digestible hierarchy or text summary. We reanalyze over 70 TREC tracks from the past 28 years, showing that roughly half undersample top ranked documents and nearly all undersample tail documents. We show that in the 2020 Deep Learning tracks, neural systems were actually near-optimal at top-ranked documents, compared to only modest gains over BM25 on tail documents. Our analysis is based on a simple new systems-oriented metric, 'atomized search length', which is capable of accurately and evenly measuring all relevant documents at any depth.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
K-Nearest Neighbor Classification Using Anatomized Data
This paper analyzes k nearest neighbor classification with training data anonymized using anatomy. Anatomy preserves all data values, but introduces uncertainty in the mapping between identifying and sensitive values. We…
AnatomyClassificationGeneral ClassificationChemDFM-R: A Chemical Reasoning LLM Enhanced with Atomized Chemical Knowledge
Atomized chemical knowledge, such as functional group information of molecules and reactions, plays a pivotal intermediate role in the reasoning process that connects molecular structures with their properties and reacti…
AtomGS: Atomizing Gaussian Splatting for High-Fidelity Radiance Field
3D Gaussian Splatting (3DGS) has recently advanced radiance field reconstruction by offering superior capabilities for novel view synthesis and real-time rendering speed. However, its strategy of blending optimization an…
3DGSNovel View SynthesisTriangular code: Near-optimal linear time fountain code
In this paper, we propose Triangular Code (TC), a new class of fountain code with near-zero redundancy and linear encoding and decoding computational complexities of OðLklog kÞ, where k is the packet batch size and L is …
DecoderTWIN V2: Scaling Ultra-Long User Behavior Sequence Modeling for Enhanced CTR Prediction at Kuaishou
The significance of modeling long-term user interests for CTR prediction tasks in large-scale recommendation systems is progressively gaining attention among researchers and practitioners. Existing work, such as SIM and …
Click-Through Rate PredictionRecommendation Systems