To Ship or Not to Ship: An Extensive Evaluation of Automatic Metrics for Machine Translation

• URL: http://arxiv.org/abs/2107.10821v1
• Date: Thu, 22 Jul 2021 17:22:22 GMT
• Title: To Ship or Not to Ship: An Extensive Evaluation of Automatic Metrics for Machine Translation
• Authors: Tom Kocmi and Christian Federmann and Roman Grundkiewicz and Marcin Junczys-Dowmunt and Hitokazu Matsushita and Arul Menezes
• Abstract summary: 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.
• Score: 5.972205906525993
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Automatic metrics are commonly used as the exclusive tool for declaring the superiority of one machine translation system's quality over another. The community choice of automatic metric guides research directions and industrial developments by deciding which models are deemed better. Evaluating metrics correlations has been limited to a small collection of human judgements. In this paper, we corroborate how reliable metrics are in contrast to human judgements on - to the best of our knowledge - the largest collection of human judgements. We investigate which metrics have the highest accuracy to make system-level quality rankings for pairs of systems, taking human judgement as a gold standard, which is the closest scenario to the real metric usage. Furthermore, we evaluate the performance of various metrics across different language pairs and domains. Lastly, we show that the sole use of BLEU negatively affected the past development of improved models. We release the collection of human judgements of 4380 systems, and 2.3 M annotated sentences for further analysis and replication of our work.

Related papers

• 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)
• 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)
• Extrinsic Evaluation of Machine Translation Metrics [78.75776477562087]
  It is unclear if automatic metrics are reliable at distinguishing good translations from bad translations at the sentence level. We evaluate the segment-level performance of the most widely used MT metrics (chrF, COMET, BERTScore, etc.) on three downstream cross-lingual tasks. Our experiments demonstrate that all metrics exhibit negligible correlation with the extrinsic evaluation of the downstream outcomes.
  arXiv  Detail & Related papers  (2022-12-20T14:39:58Z)
• 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)
• Bidimensional Leaderboards: Generate and Evaluate Language Hand in Hand [117.62186420147563]
  We propose a generalization of leaderboards, bidimensional leaderboards (Billboards) Unlike conventional unidimensional leaderboards that sort submitted systems by predetermined metrics, a Billboard accepts both generators and evaluation metrics as competing entries. We demonstrate that a linear ensemble of a few diverse metrics sometimes substantially outperforms existing metrics in isolation.
  arXiv  Detail & Related papers  (2021-12-08T06:34:58Z)
• Experts, Errors, and Context: A Large-Scale Study of Human Evaluation for Machine Translation [19.116396693370422]
  We propose an evaluation methodology grounded in explicit error analysis, based on the Multidimensional Quality Metrics framework. We carry out the largest MQM research study to date, scoring the outputs of top systems from the WMT 2020 shared task in two language pairs. We analyze the resulting data extensively, finding among other results a substantially different ranking of evaluated systems from the one established by the WMT crowd workers.
  arXiv  Detail & Related papers  (2021-04-29T16:42:09Z)
• Tangled up in BLEU: Reevaluating the Evaluation of Automatic Machine Translation Evaluation Metrics [64.88815792555451]
  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.
  arXiv  Detail & Related papers  (2020-06-11T09:12:53Z)
• A Human Evaluation of AMR-to-English Generation Systems [13.10463139842285]
  We present the results of a new human evaluation which collects fluency and adequacy scores, as well as categorization of error types. We discuss the relative quality of these systems and how our results compare to those of automatic metrics.
  arXiv  Detail & Related papers  (2020-04-14T21:41:30Z)
• BLEU might be Guilty but References are not Innocent [34.817010352734]
  We study different methods to collect references and compare their value in automated evaluation. Motivated by the finding that typical references exhibit poor diversity, concentrating around translationese language, we develop a paraphrasing task. Our method yields higher correlation with human judgment not only for the submissions of WMT 2019 English to German, but also for Back-translation and APE augmented MT output.
  arXiv  Detail & Related papers  (2020-04-13T16:49:09Z)

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.