Tangled up in BLEU: Reevaluating the Evaluation of Automatic Machine Translation Evaluation Metrics

• URL: http://arxiv.org/abs/2006.06264v2
• Date: Fri, 12 Jun 2020 04:35:41 GMT
• Title: Tangled up in BLEU: Reevaluating the Evaluation of Automatic Machine Translation Evaluation Metrics
• Authors: Nitika Mathur, Timothy Baldwin and Trevor Cohn
• Abstract summary: We show that current methods for judging metrics are highly sensitive to the translations used for assessment. We develop a method for thresholding performance improvement under an automatic metric against human judgements.
• Score: 64.88815792555451
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Automatic metrics are fundamental for the development and evaluation of machine translation systems. Judging whether, and to what extent, automatic metrics concur with the gold standard of human evaluation is not a straightforward problem. We show that current methods for judging metrics are highly sensitive to the translations used for assessment, particularly the presence of outliers, which often leads to falsely confident conclusions about a metric's efficacy. Finally, we turn to pairwise system ranking, developing a method for thresholding performance improvement under an automatic metric against human judgements, which allows quantification of type I versus type II errors incurred, i.e., insignificant human differences in system quality that are accepted, and significant human differences that are rejected. Together, these findings suggest improvements to the protocols for metric evaluation and system performance evaluation in machine translation.

Related papers

• Guardians of the Machine Translation Meta-Evaluation: Sentinel Metrics Fall In! [80.3129093617928]
  Annually, at the Conference of Machine Translation (WMT), the Metrics Shared Task organizers conduct the meta-evaluation of Machine Translation (MT) metrics. This work highlights two issues with the meta-evaluation framework currently employed in WMT, and assesses their impact on the metrics rankings. We introduce the concept of sentinel metrics, which are designed explicitly to scrutinize the meta-evaluation process's accuracy, robustness, and fairness.
  arXiv  Detail & Related papers  (2024-08-25T13:29:34Z)
• Can Automatic Metrics Assess High-Quality Translations? [28.407966066693334]
  We show that current metrics are insensitive to nuanced differences in translation quality. This effect is most pronounced when the quality is high and the variance among alternatives is low. Using the MQM framework as the gold standard, we systematically stress-test the ability of current metrics to identify translations with no errors as marked by humans.
  arXiv  Detail & Related papers  (2024-05-28T16:44:02Z)
• Is Reference Necessary in the Evaluation of NLG Systems? When and Where? [58.52957222172377]
  We show that reference-free metrics exhibit a higher correlation with human judgment and greater sensitivity to deficiencies in language quality. Our study can provide insight into the appropriate application of automatic metrics and the impact of metric choice on evaluation performance.
  arXiv  Detail & Related papers  (2024-03-21T10:31:11Z)
• Convergences and Divergences between Automatic Assessment and Human Evaluation: Insights from Comparing ChatGPT-Generated Translation and Neural Machine Translation [1.6982207802596105]
  This study investigates the convergences and divergences between automated metrics and human evaluation. To perform automatic assessment, four automated metrics are employed, while human evaluation incorporates the DQF-MQM error typology and six rubrics. Results underscore the indispensable role of human judgment in evaluating the performance of advanced translation tools.
  arXiv  Detail & Related papers  (2024-01-10T14:20:33Z)
• BLEURT Has Universal Translations: An Analysis of Automatic Metrics by Minimum Risk Training [64.37683359609308]
  In this study, we analyze various mainstream and cutting-edge automatic metrics from the perspective of their guidance for training machine translation systems. We find that certain metrics exhibit robustness defects, such as the presence of universal adversarial translations in BLEURT and BARTScore. In-depth analysis suggests two main causes of these robustness deficits: distribution biases in the training datasets, and the tendency of the metric paradigm.
  arXiv  Detail & Related papers  (2023-07-06T16:59:30Z)
• Correction of Errors in Preference Ratings from Automated Metrics for Text Generation [4.661309379738428]
  We propose a statistical model of Text Generation evaluation that accounts for the error-proneness of automated metrics. We show that our model enables an efficient combination of human and automated ratings to remedy the error-proneness of the automated metrics.
  arXiv  Detail & Related papers  (2023-06-06T17:09:29Z)
• The Glass Ceiling of Automatic Evaluation in Natural Language Generation [60.59732704936083]
  We take a step back and analyze recent progress by comparing the body of existing automatic metrics and human metrics. Our extensive statistical analysis reveals surprising findings: automatic metrics -- old and new -- are much more similar to each other than to humans.
  arXiv  Detail & Related papers  (2022-08-31T01:13:46Z)
• Re-Examining System-Level Correlations of Automatic Summarization Evaluation Metrics [64.81682222169113]
  How reliably an automatic summarization evaluation metric replicates human judgments of summary quality is quantified by system-level correlations. We identify two ways in which the definition of the system-level correlation is inconsistent with how metrics are used to evaluate systems in practice.
  arXiv  Detail & Related papers  (2022-04-21T15:52:14Z)
• To Ship or Not to Ship: An Extensive Evaluation of Automatic Metrics for Machine Translation [5.972205906525993]
  We investigate which metrics have the highest accuracy to make system-level quality rankings for pairs of systems. We show that the sole use of BLEU negatively affected the past development of improved models.
  arXiv  Detail & Related papers  (2021-07-22T17:22:22Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.