MétaCan
Menu
Back to cohort
Record W4399298003 · doi:10.1017/nlp.2024.5

Calibration and context in human evaluation of machine translation

2024· article· en· W4399298003 on OpenAlexaff
Rebecca Knowles, Chi-kiu Lo

Bibliographic record

VenueNatural language processing. · 2024
Typearticle
Languageen
FieldComputer Science
TopicNatural Language Processing Techniques
Canadian institutionsNational Research Council Canada
Fundersnot available
KeywordsCalibrationContext (archaeology)Translation (biology)Machine translationComputer scienceArtificial intelligenceNatural language processingMachine learningChemistryBiologyMathematicsStatisticsBiochemistry

Abstract

fetched live from OpenAlex

Abstract Human evaluation of machine translation is considered the “gold standard” for evaluation, but it remains a challenging task for which to define best practices. Recent work has focused on incorporating intersentential context into human evaluation, to better distinguish between high-performing machine translation systems and human translations. In this work, we examine several ways that such context influences evaluation and evaluation protocols. We take a close look at annotator variation through the lens of calibration sets and focus on the implications for context-aware evaluation protocols. We then demonstrate one way in which degraded target-side intersentential context can influence annotator scores of individual sentences, a finding that supports the context-aware approach to evaluation and which also has implications for best practices in evaluation protocols.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.123
metaresearch head score (Gemma)0.389
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesMetaresearch
Consensus categoriesnone
DomainCandidate signal: Evaluation · Consensus signal: none
Study designCandidate signal: Observational · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.877
Threshold uncertainty score0.653

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.1230.389
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0030.002
Science and technology studies0.0020.004
Scholarly communication0.0050.005
Open science0.0020.008
Research integrity0.0020.002
Insufficient payload (model declined to judge)0.0020.001

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.020
GPT teacher head0.330
Teacher spread0.310 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

Study designObservational
DomainEvaluation
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations3
Published2024
Admission routes1
Has abstractyes

Explore more

Same venueNatural language processing.Same topicNatural Language Processing TechniquesFrench-language works237,207