Dontopedia

Bleu Score Calculation

From Dontopedia, the open, paraconsistent wiki. (Last updated 2026-06-11.)

Bleu Score Calculation has 10 facts recorded in Dontopedia across 3 references, with 2 live disagreements.

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

Mostly:uses(3), has input(2), imported from(1)

Maturity scale raw canonical shape-checked rule-derived certified

Inbound mentions (2)

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.

demonstratesDemonstrates(1)

hasComponentHas Component(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
Usessentence_bleu[1]
Usesoriginal.split()[1]
Usesreformulated.split()[1]
Has InputReferences[2]
Has InputHypotheses[2]
Imported Fromnltk.translate.bleu_score[1]
Rdf:typeProcess[2]
Has OutputBleu Score[2]
Has Code SnippetBleu Score Code[3]
PurposeEvaluate Reformulation Accuracy[3]

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.

usesbeam/97ef0996-2bbf-4217-af6b-6a0f7a933ea0
sentence_bleu
importedFrombeam/97ef0996-2bbf-4217-af6b-6a0f7a933ea0
nltk.translate.bleu_score
usesbeam/97ef0996-2bbf-4217-af6b-6a0f7a933ea0
original.split()
usesbeam/97ef0996-2bbf-4217-af6b-6a0f7a933ea0
reformulated.split()
typebeam/67650a9a-a8c9-4ad5-94a0-9080d151ac84
ex:Process
hasInputbeam/67650a9a-a8c9-4ad5-94a0-9080d151ac84
ex:references
hasInputbeam/67650a9a-a8c9-4ad5-94a0-9080d151ac84
ex:hypotheses
hasOutputbeam/67650a9a-a8c9-4ad5-94a0-9080d151ac84
ex:bleu-score
hasCodeSnippetbeam/b1c43907-80fa-4804-9f16-0edd887a0129
ex:bleu-score-code
purposebeam/b1c43907-80fa-4804-9f16-0edd887a0129
ex:evaluate-reformulation-accuracy

References (3)

3 references
  1. ctx:claims/beam/97ef0996-2bbf-4217-af6b-6a0f7a933ea0
    • full textbeam-chunk
      text/plain1 KBdoc:beam/97ef0996-2bbf-4217-af6b-6a0f7a933ea0
      Show excerpt
      eval_dataset=eval_dataset, ) trainer.train() ``` ### Evaluation Metrics To evaluate the quality of reformulated queries, you can use metrics like BLEU or ROUGE: ```python from nltk.translate.bleu_score import sentence_bleu def eval
  2. ctx:claims/beam/67650a9a-a8c9-4ad5-94a0-9080d151ac84
  3. ctx:claims/beam/b1c43907-80fa-4804-9f16-0edd887a0129
    • full textbeam-chunk
      text/plain1 KBdoc:beam/b1c43907-80fa-4804-9f16-0edd887a0129
      Show excerpt
      # Calculate the BLEU score references = outputs.tolist() hypotheses = reformulated_outputs bleu_scores = [] for ref, hyp in zip(references, hypotheses): bleu_scores.append(sentence_bleu([ref.split()], hyp.split())) bleu_score = sum(b

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.