Bm25 Retrieval
From Dontopedia, the open, paraconsistent wiki. (Last updated 2026-06-08.)
sameAs to 1 other subject: Sparse RetrievalReview & merge →Bm25 Retrieval has 10 facts recorded in Dontopedia across 3 references, with 2 live disagreements.
Mostly:rdf:type(3), has parameter(2), complements(1)
Maturity scale
raw canonical shape-checked rule-derived certifiedInbound mentions (5)
Other subjects in dontopedia point AT this entity as a value. These are inverse relationships — e.g. "X motherOf this subject" — and answer questions the forward facts can't. Grouped by predicate.
callsFunctionCalls Function(1)
- Hybrid Retrieval Function
ex:hybrid-retrieval-function
complementsComplements(1)
- Dense Retrieval Method
ex:dense-retrieval-method
computedByComputed by(1)
- Bm25 Scores
ex:bm25-scores
includesIncludes(1)
- Retrieval Methods
ex:retrieval-methods
integratesIntegrates(1)
- Hybrid System
ex:hybrid-system
Other facts (10)
The long tail: predicates that appear too rarely to warrant their own section. Filter or scroll to find a specific one. Each row links to its source.
| Predicate | Value | Ref |
|---|---|---|
| Rdf:type | Sparse Retrieval Method | [1] |
| Rdf:type | Function | [2] |
| Rdf:type | Information Retrieval Method | [3] |
| Has Parameter | query | [2] |
| Has Parameter | documents | [2] |
| Complements | Dense Retrieval Method | [1] |
| Function Name | bm25_retrieval | [2] |
| Called by | Hybrid Sparse Dense Retrieval | [2] |
| Alias | Sparse Retrieval | [2] |
| Returns | Bm25 Scores Array | [2] |
Timeline
Timeline axis is valid_time — when each source says the fact was true in the world, not when Dontopedia learned about it. Retracted rows are kept for provenance; coloured stripes indicate the context kind.
References (3)
ctx:claims/beam/b0390377-17cd-4838-999f-26ca02c6c6a4- full textbeam-chunktext/plain963 B
doc:beam/b0390377-17cd-4838-999f-26ca02c6c6a4Show excerpt
- We use a pre-trained BERT model to generate embeddings for documents and the query. - `cosine_similarity` computes the similarity between the query embedding and document embeddings. 3. **Combining Scores**: - We combine the BM2…
ctx:claims/beam/07b00e3a-dd0e-40bb-a9be-bbdf1ac254da- full textbeam-chunktext/plain1 KB
doc:beam/07b00e3a-dd0e-40bb-a9be-bbdf1ac254daShow excerpt
with torch.no_grad(): doc_outputs = model(**doc_inputs) query_outputs = model(**query_inputs) doc_embeddings = doc_outputs.last_hidden_state.mean(dim=1) query_embedding = query_outputs.last_hidden_state.mean(dim…
ctx:claims/beam/23c0eddb-0929-4239-8d55-13531af3e8f5- full textbeam-chunktext/plain1 KB
doc:beam/23c0eddb-0929-4239-8d55-13531af3e8f5Show excerpt
- **Average Precision (AP)**: Measure of precision at each relevant document. 4. **Mean Scores**: Calculate the mean of each metric across all queries. ### Additional Metrics 1. **Precision@k**: Precision of the top-k retrieved documen…
See also
Keep researching
Missing something or suspicious of what's here? Kick off a research session — a Claude agent will investigate, cite its sources, and file new facts into a dedicated context you can review before accepting into the shared view.