Claims

BLEU produced low scores when ensembled with other techniques, possibly due to brevity penalty over-penalization, so it was excluded from the ensemble

Claim · All claims
Evidence · 1 study · design r2 · q1
Currency · newest study 2009 · not yet checked against its sources · not reviewed by a person

Subclaims

Reading the evidence codes

q is the design tier, i the impact, n the sample, and the kind with its r the rigour judged within that kind: what each code means.

This claim: no standardized effect is recorded in observations/ for it yet, so no benchmark reading is possible.

q1 i? BLEU was dropped from the ensemble after producing low scores, attributed to possible brevity penalty over-penalization. → Automatic Summary Assessment for Intelligent Tutoring Systems 2009

Evidence

Automatic Summary Assessment for Intelligent Tutoring Systems 2009

Automatic Summary Assessment for Intelligent Tutoring Systems. (2009). Preprint submitted to Elsevier February 26, 2009. https://doi.org/10.1016/j.compedu.2009.05.008

q1 · i? · design · r2

Authors' interpretation of their evaluation of four techniques: BLEU "produced low scores in its performance when ensembled with other techniques", attributed to "the brevity penalty over penalization". This is an author interpretation rather than a tested result.

"However, we found that BLEU produced low scores in its perfor- mance when ensembled with other techniques. This might due to the brevity penalty over penalization."

Discussion

Page metadata
Field Value
type claim
id bleu-excluded-brevity-penalty
title BLEU produced low scores when ensembled with other techniques, possibly due to brevity penalty over-penalization, so it was excluded from the ensemble
description BLEU produced low scores when ensembled with other techniques, possibly due to brevity penalty over-penalization, so it was excluded from the ensemble
status review
evidence_strength weak
newest_evidence 2009
generated by process:wiki-ingest on 2026-10-30
trust unverified — no one has confirmed this page's content
sources 1 — automatic-summary-assessment-for-intelligent-tutoring-systems-2009

Frontmatter is the page's machine-readable record — see the Schema & Guide.