Quality and Quantity of Machine Translation References for Automatic Metrics

• URL: http://arxiv.org/abs/2401.01283v5
• Date: Wed, 10 Apr 2024 13:05:42 GMT
• Title: Quality and Quantity of Machine Translation References for Automatic Metrics
• Authors: Vilém Zouhar, Ondřej Bojar,
• Abstract summary: Higher-quality references lead to better metric correlations with humans at the segment-level. The references from vendors of different qualities can be mixed together and improve metric success. These findings can be used by evaluators of shared tasks when references need to be created under a certain budget.
• Score: 4.824118883700288
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Automatic machine translation metrics typically rely on human translations to determine the quality of system translations. Common wisdom in the field dictates that the human references should be of very high quality. However, there are no cost-benefit analyses that could be used to guide practitioners who plan to collect references for machine translation evaluation. We find that higher-quality references lead to better metric correlations with humans at the segment-level. Having up to 7 references per segment and taking their average (or maximum) helps all metrics. Interestingly, the references from vendors of different qualities can be mixed together and improve metric success. Higher quality references, however, cost more to create and we frame this as an optimization problem: given a specific budget, what references should be collected to maximize metric success. These findings can be used by evaluators of shared tasks when references need to be created under a certain budget.

Related papers

• Mitigating the Impact of Reference Quality on Evaluation of Summarization Systems with Reference-Free Metrics [4.881135687863645]
  We introduce a reference-free metric that correlates well with human evaluated relevance, while being very cheap to compute. We show that this metric can also be used alongside reference-based metrics to improve their robustness in low quality reference settings.
  arXiv  Detail & Related papers  (2024-10-08T11:09:25Z)
• 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)
• Evaluating Optimal Reference Translations [4.956416618428049]
  We propose a methodology for creating more reliable document-level human reference translations. We evaluate the obtained document-level optimal reference translations in comparison with "standard" ones.
  arXiv  Detail & Related papers  (2023-11-28T13:50:50Z)
• 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)
• On the Limitations of Reference-Free Evaluations of Generated Text [64.81682222169113]
  We show that reference-free metrics are inherently biased and limited in their ability to evaluate generated text. We argue that they should not be used to measure progress on tasks like machine translation or summarization.
  arXiv  Detail & Related papers  (2022-10-22T22:12:06Z)
• Rethink about the Word-level Quality Estimation for Machine Translation from Human Judgement [57.72846454929923]
  We create a benchmark dataset, emphHJQE, where the expert translators directly annotate poorly translated words. We propose two tag correcting strategies, namely tag refinement strategy and tree-based annotation strategy, to make the TER-based artificial QE corpus closer to emphHJQE. The results show our proposed dataset is more consistent with human judgement and also confirm the effectiveness of the proposed tag correcting strategies.
  arXiv  Detail & Related papers  (2022-09-13T02:37:12Z)
• Measuring Uncertainty in Translation Quality Evaluation (TQE) [62.997667081978825]
  This work carries out motivated research to correctly estimate the confidence intervals citeBrown_etal2001Interval depending on the sample size of the translated text. The methodology we applied for this work is from Bernoulli Statistical Distribution Modelling (BSDM) and Monte Carlo Sampling Analysis (MCSA)
  arXiv  Detail & Related papers  (2021-11-15T12:09:08Z)
• 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)
• REAM$\sharp$: An Enhancement Approach to Reference-based Evaluation Metrics for Open-domain Dialog Generation [63.46331073232526]
  We present an enhancement approach to Reference-based EvAluation Metrics for open-domain dialogue systems. A prediction model is designed to estimate the reliability of the given reference set. We show how its predicted results can be helpful to augment the reference set, and thus improve the reliability of the metric.
  arXiv  Detail & Related papers  (2021-05-30T10:04:13Z)
• Human-Paraphrased References Improve Neural Machine Translation [33.86920777067357]
  We show that tuning to paraphrased references produces a system that is significantly better according to human judgment. Our work confirms the finding that paraphrased references yield metric scores that correlate better with human judgment.
  arXiv  Detail & Related papers  (2020-10-20T13:14:57Z)
• 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.