Pitfalls and Outlooks in Using COMET

• URL: http://arxiv.org/abs/2408.15366v3
• Date: Mon, 30 Sep 2024 13:44:11 GMT
• Title: Pitfalls and Outlooks in Using COMET
• Authors: Vilém Zouhar, Pinzhen Chen, Tsz Kin Lam, Nikita Moghe, Barry Haddow,
• Abstract summary: The COMET metric has blazed a trail in the machine translation community, given its strong correlation with human translation quality. We investigate three aspects of the COMET metric: technical: obsolete software versions and compute precision; data: empty content, language mismatch, and translationese at test time; usage and reporting. We release the sacreCOMET package that can generate a signature for the software and model configuration as well as an appropriate citation.
• Score: 22.016569792620295
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The COMET metric has blazed a trail in the machine translation community, given its strong correlation with human judgements of translation quality. Its success stems from being a modified pre-trained multilingual model finetuned for quality assessment. However, it being a machine learning model also gives rise to a new set of pitfalls that may not be widely known. We investigate these unexpected behaviours from three aspects: 1) technical: obsolete software versions and compute precision; 2) data: empty content, language mismatch, and translationese at test time as well as distribution and domain biases in training; 3) usage and reporting: multi-reference support and model referencing in the literature. All of these problems imply that COMET scores are not comparable between papers or even technical setups and we put forward our perspective on fixing each issue. Furthermore, we release the sacreCOMET package that can generate a signature for the software and model configuration as well as an appropriate citation. The goal of this work is to help the community make more sound use of the COMET metric.

Related papers

• Improving Language Models Trained on Translated Data with Continual Pre-Training and Dictionary Learning Analysis [3.16714407449467]
  We investigate the role of translation and synthetic data in training language models. We translate TinyStories, a dataset of 2.2M short stories for 3-4 year old children, from English to Arabic using the open NLLB-3B MT model. To rectify these issues, we pre-train the models with a small dataset of synthesized high-quality Arabic stories.
  arXiv  Detail & Related papers  (2024-05-23T07:53:04Z)
• 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)
• On Search Strategies for Document-Level Neural Machine Translation [51.359400776242786]
  Document-level neural machine translation (NMT) models produce a more consistent output across a document. In this work, we aim to answer the question how to best utilize a context-aware translation model in decoding.
  arXiv  Detail & Related papers  (2023-06-08T11:30:43Z)
• 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)
• 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)
• BLEU, METEOR, BERTScore: Evaluation of Metrics Performance in Assessing Critical Translation Errors in Sentiment-oriented Text [1.4213973379473654]
  Machine Translation (MT) of the online content is commonly used to process posts written in several languages. In this paper, we assess the ability of automatic quality metrics to detect critical machine translation errors. We conclude that there is a need for fine-tuning of automatic metrics to make them more robust in detecting sentiment critical errors.
  arXiv  Detail & Related papers  (2021-09-29T07:51:17Z)
• When Does Translation Require Context? A Data-driven, Multilingual Exploration [71.43817945875433]
  proper handling of discourse significantly contributes to the quality of machine translation (MT) Recent works in context-aware MT attempt to target a small set of discourse phenomena during evaluation. We develop the Multilingual Discourse-Aware benchmark, a series of taggers that identify and evaluate model performance on discourse phenomena.
  arXiv  Detail & Related papers  (2021-09-15T17:29:30Z)
• Transfer Learning for Mining Feature Requests and Bug Reports from Tweets and App Store Reviews [4.446419663487345]
  Existing approaches fail to detect feature requests and bug reports with high Recall and acceptable Precision. We train both monolingual and multilingual BERT models and compare the performance with state-of-the-art methods.
  arXiv  Detail & Related papers  (2021-08-02T06:51:13Z)
• ChrEnTranslate: Cherokee-English Machine Translation Demo with Quality Estimation and Corrective Feedback [70.5469946314539]
  ChrEnTranslate is an online machine translation demonstration system for translation between English and an endangered language Cherokee. It supports both statistical and neural translation models as well as provides quality estimation to inform users of reliability.
  arXiv  Detail & Related papers  (2021-07-30T17:58:54Z)
• Patching as Translation: the Data and the Metaphor [18.22949296398319]
  We show that "software patching is like language translation" We show how a more principled approach to model design, based on our empirical findings and general knowledge of software development, can lead to better solutions. We implement such models ourselves as "proof-of-concept" tools and empirically confirm that they behave in a fundamentally different, more effective way than the studied translation-based architectures.
  arXiv  Detail & Related papers  (2020-08-24T21:05:27Z)

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.