MétaCan
Menu
Back to cohort
Record W2065198647 · doi:10.7202/1006181ar

A Corpus-Based Evaluation Approach to Translation Improvement

2011· article· en· W2065198647 on OpenAlexvenueno aff
Ghodrat Hassani

Bibliographic record

VenueMeta Journal des traducteurs · 2011
Typearticle
Languageen
FieldArts and Humanities
TopicTranslation Studies and Practices
Canadian institutionsnot available
Fundersnot available
KeywordsObjectivity (philosophy)SubjectivityComputer scienceSharpeningQuality (philosophy)Artificial intelligenceNatural language processingEpistemology

Abstract

fetched live from OpenAlex

In professional settings translation evaluation has always been weighed down by the albatross of subjectivity to the detriment of both evaluators as clients and translators as service providers. But perhaps this burden can be lightened, through ongoing evaluator feedback and exchange that foster objectivity among the evaluators while sharpening the professional skills and recognition of the translators. The purpose of this paper is to explore the promising avenues that a corpus-based evaluation approach can possibly offer them. Using the Corpus of Contemporary American English (COCA) for evaluation purposes in a professional setting, the approach adopted for this study regards translation evaluation as a means to a worthwhile end, in a nutshell, better translations. This approach also illustrates how the unique features of the corpus can minimize subjectivity in translation evaluation; this in turn leads to translations of superior quality.

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)0.097
metaresearch head score (Gemma)0.140
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Observational · Consensus signal: none
GenreCandidate signal: Methods · Consensus signal: Methods
Teacher disagreement score0.097
Threshold uncertainty score0.514

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0970.140
Meta-epidemiology (narrow)0.0020.001
Meta-epidemiology (broad)0.0020.001
Bibliometrics0.0130.012
Science and technology studies0.0050.006
Scholarly communication0.0130.012
Open science0.0040.008
Research integrity0.0030.004
Insufficient payload (model declined to judge)0.0100.002

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 head0.240
GPT teacher head0.318
Teacher spread0.078 · 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.

The models applied no category: nothing in the taxonomy fit this work.
Study designObservational
Domainnot available
GenreMethods

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

Citations12
Published2011
Admission routes1
Has abstractyes

Explore more

Same venueMeta Journal des traducteursSame topicTranslation Studies and PracticesFrench-language works237,207