Sparse Retrieval
الاسترجاع المتناثر
أسلوب استرجاع تقليدي يُمثِّل النصوص كمتجهات متناثرة (معظم قيمها أصفار) بناءً على تكرار الكلمات. يعتمد على مطابقة المصطلحات اللفظية، مثل TF-IDF وBM25.
A traditional retrieval approach that represents documents as sparse vectors (mostly zeros) based on word frequency. Relies on lexical term matching, e.g. TF-IDF and BM25.
Also translated asالاسترجاع بالمتجهات المتناثرة، الاسترجاع القائم على المفردات
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 ✦
- Dense Passage Retrieval for Open-Domain Question Answering2020in the sky ✦
- Dense Passage Retrieval for Open-Domain Question Answering2020in the sky ✦
- HyDE: Precise Zero-Shot Dense Retrieval without Relevance Labels2022in the sky ✦
- SWE-bench: Can Language Models Resolve Real-World GitHub Issues?2024in the sky ✦
- SWE-bench: Can Language Models Resolve Real-World GitHub Issues?2024in the sky ✦