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.
Mostly:uses(3), has input(2), imported from(1)
Maturity scale
raw canonical shape-checked rule-derived certifiedInbound 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)
- Code Example
ex:code-example
hasComponentHas Component(1)
- Code Purpose
ex:code-purpose
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 |
|---|---|---|
| Uses | sentence_bleu | [1] |
| Uses | original.split() | [1] |
| Uses | reformulated.split() | [1] |
| Has Input | References | [2] |
| Has Input | Hypotheses | [2] |
| Imported From | nltk.translate.bleu_score | [1] |
| Rdf:type | Process | [2] |
| Has Output | Bleu Score | [2] |
| Has Code Snippet | Bleu Score Code | [3] |
| Purpose | Evaluate 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.
References (3)
ctx:claims/beam/97ef0996-2bbf-4217-af6b-6a0f7a933ea0- full textbeam-chunktext/plain1 KB
doc:beam/97ef0996-2bbf-4217-af6b-6a0f7a933ea0Show 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…
ctx:claims/beam/67650a9a-a8c9-4ad5-94a0-9080d151ac84ctx:claims/beam/b1c43907-80fa-4804-9f16-0edd887a0129- full textbeam-chunktext/plain1 KB
doc:beam/b1c43907-80fa-4804-9f16-0edd887a0129Show 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.