arXiv:2012.08020
공식 코드 · Papers with Code
Traditional IR rivals neural models on the MS MARCO Document Ranking Leaderboard
원문 초록
This short document describes a traditional IR system that achieved MRR@100 equal to 0.298 on the MS MARCO Document Ranking leaderboard (on 2020-12-06). Although inferior to most BERT-based models, it outperformed several neural runs (as well as all non-neural ones), including two submissions that used a large pretrained Transformer model for re-ranking. We provide software and data to reproduce our results.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Distillation and Refinement of Reasoning in Small Language Models for Document Re-ranking
PromptReps: Prompting Large Language Models to Generate Dense and Sparse Representations for Zero-Shot Document Retrieval
Graph-Based Re-ranking: Emerging Techniques, Limitations, and Opportunities
Efficient Document Ranking with Learnable Late Interactions
RAG-VisualRec: An Open Resource for Vision- and Text-Enhanced Retrieval-Augmented Generation in Recommendation
IRanker: Towards Ranking Foundation Model
토론
이 논문과 연결된 포럼 글이 아직 없습니다.