Dontopedia

Bm25 Retrieval

From Dontopedia, the open, paraconsistent wiki. (Last updated 2026-06-08.)

Linked via sameAs to 1 other subject: Sparse RetrievalReview & merge →

Bm25 Retrieval has 10 facts recorded in Dontopedia across 3 references, with 2 live disagreements.

10 facts·7 predicates·3 sources·2 in dispute

Mostly:rdf:type(3), has parameter(2), complements(1)

Maturity scale raw canonical shape-checked rule-derived certified

Inbound 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)

complementsComplements(1)

computedByComputed by(1)

includesIncludes(1)

integratesIntegrates(1)

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.

10 facts
PredicateValueRef
Rdf:typeSparse Retrieval Method[1]
Rdf:typeFunction[2]
Rdf:typeInformation Retrieval Method[3]
Has Parameterquery[2]
Has Parameterdocuments[2]
ComplementsDense Retrieval Method[1]
Function Namebm25_retrieval[2]
Called byHybrid Sparse Dense Retrieval[2]
AliasSparse Retrieval[2]
ReturnsBm25 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.

typebeam/b0390377-17cd-4838-999f-26ca02c6c6a4
ex:SparseRetrievalMethod
complementsbeam/b0390377-17cd-4838-999f-26ca02c6c6a4
ex:dense-retrieval-method
typebeam/07b00e3a-dd0e-40bb-a9be-bbdf1ac254da
ex:Function
functionNamebeam/07b00e3a-dd0e-40bb-a9be-bbdf1ac254da
bm25_retrieval
calledBybeam/07b00e3a-dd0e-40bb-a9be-bbdf1ac254da
ex:hybrid-sparse-dense-retrieval
hasParameterbeam/07b00e3a-dd0e-40bb-a9be-bbdf1ac254da
query
hasParameterbeam/07b00e3a-dd0e-40bb-a9be-bbdf1ac254da
documents
aliasbeam/07b00e3a-dd0e-40bb-a9be-bbdf1ac254da
ex:sparse-retrieval
returnsbeam/07b00e3a-dd0e-40bb-a9be-bbdf1ac254da
ex:bm25-scores-array
typebeam/23c0eddb-0929-4239-8d55-13531af3e8f5
ex:InformationRetrievalMethod

References (3)

3 references
  1. ctx:claims/beam/b0390377-17cd-4838-999f-26ca02c6c6a4
    • full textbeam-chunk
      text/plain963 Bdoc:beam/b0390377-17cd-4838-999f-26ca02c6c6a4
      Show 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
  2. ctx:claims/beam/07b00e3a-dd0e-40bb-a9be-bbdf1ac254da
    • full textbeam-chunk
      text/plain1 KBdoc:beam/07b00e3a-dd0e-40bb-a9be-bbdf1ac254da
      Show 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
  3. ctx:claims/beam/23c0eddb-0929-4239-8d55-13531af3e8f5
    • full textbeam-chunk
      text/plain1 KBdoc:beam/23c0eddb-0929-4239-8d55-13531af3e8f5
      Show 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.