Beyond correlation: making sense of the score differences of new MT evaluation metrics
Bibliographic record
Abstract
While many new automatic metrics for machine translation valuation have been proposed in recent years, BLEU scores are still used as the primary metric in the vast majority of MT research papers. There are many reasons that researchers may be reluctant to switch to new metrics, from external pressures (reviewers, prior work) to the ease of use of metric toolkits. Another reason is a lack of intuition about the meaning of novel metric scores. In this work, we examine “rules of thumb” about metric score differences and how they do (and do not) correspond to human judgments of statistically significant differences between systems. In particular, we show that common rules of thumb about BLEU score differences do not in fact guarantee that human annotators will find significant differences between systems. We also show ways in which these rules of thumb fail to generalize across translation directions or domains.
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 imitationNot 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.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.089 | 0.462 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.003 | 0.001 |
| Bibliometrics | 0.010 | 0.010 |
| Science and technology studies | 0.002 | 0.007 |
| Scholarly communication | 0.011 | 0.018 |
| Open science | 0.004 | 0.007 |
| Research integrity | 0.003 | 0.008 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
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.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
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".