BM25
BM25
خوارزمية استرجاع معلومات كلاسيكية تُرتِّب المستندات حسب تكرار الكلمات المشتركة مع الاستعلام، مع مراعاة طول المستند وندرة المصطلح. الأساس المعياري للاسترجاع المتناثر.
A classic information retrieval algorithm that ranks documents by frequency of query term matches, accounting for document length and term rarity. The standard baseline for sparse retrieval.
Also translated asخوارزمية BM25، أوكابي BM25
First appears in this corpus in: Okapi at TREC-3 (1994)
Appears in these papers
- Okapi at TREC-31994in the sky ✦
- ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT2020in the sky ✦
- Contriever: Unsupervised Dense Information Retrieval with Contrastive Learning2022in the sky ✦
- Dense Passage Retrieval for Open-Domain Question Answering2020in the sky ✦
- Fusion-in-Decoder: Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering2021in the sky ✦
- HyDE: Precise Zero-Shot Dense Retrieval without Relevance Labels2022in the sky ✦
- REALM: Retrieval-Augmented Language Model Pre-Training2020in the sky ✦
- SWE-bench: Can Language Models Resolve Real-World GitHub Issues?2024in the sky ✦