paper-with-me

Papers

Uncertainty-Aware Machine Translation Evaluation

2021-09-13 · Findings (EMNLP) 2021 11 · Taisiya Glushkova, Chrysoula Zerva, Ricardo Rei, André F. T. Martins

Several neural-based metrics have been recently proposed to evaluate machine translation quality. However, all of them resort to point estimates, which provide limited information at segment level. This is made worse as they are trained on noisy, biased and scarce human judgements, often resulting in unreliable quality predictions. In this paper, we introduce uncertainty-aware MT evaluation and analyze the trustworthiness of the predicted quality. We combine the COMET framework with two uncertainty estimation methods, Monte Carlo dropout and deep ensembles, to obtain quality scores along with confidence intervals. We compare the performance of our uncertainty-aware MT evaluation methods across multiple language pairs from the QT21 dataset and the WMT20 metrics task, augmented with MQM annotations. We experiment with varying numbers of references and further discuss the usefulness of uncertainty-aware quality estimation (without references) to flag possibly critical translation mistakes.

📄 PDF Abstract BibTeX arXiv:2109.06352

Code (2)

Unbabel/COMET 공식 구현 pytorch
deep-spin/ua_comet 공식 구현

Tasks

Machine TranslationTranslation

Methods 이 논문이 사용한 방법론

Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Monte Carlo Dropout 설명 없음

Similar Papers 제목 키워드 기반

Uncertainty-Aware Curriculum Learning for Neural Machine Translation

2020-07-01 · ACL 2020 6 · Yikai Zhou, Baosong Yang, Derek F. Wong, Yu Wan 외

Neural machine translation (NMT) has proven to be facilitated by curriculum learning which presents examples in an easy-to-hard order at different training stages. The keys lie in the assessment of data difficulty and mo…

Machine TranslationNMTTranslation

Early-Exit and Instant Confidence Translation Quality Estimation

2025-02-20 · Vilém Zouhar, Maike Züfle, Beni Egressy, Julius Cheng 외

Quality estimation is omnipresent in machine translation, for both evaluation and generation. Unfortunately, quality estimation models are often opaque and computationally expensive, making them impractical to be part of…

Machine TranslationRerankingTranslation

Uncertainty-Aware Semantic Augmentation for Neural Machine Translation

2020-10-09 · EMNLP 2020 11 · Xiangpeng Wei, Heng Yu, Yue Hu, Rongxiang Weng 외

As a sequence-to-sequence generation task, neural machine translation (NMT) naturally contains intrinsic uncertainty, where a single sentence in one language has multiple valid counterparts in the other. However, the dom…

Machine TranslationNMTSentenceTranslation+1

Disentangling Uncertainty in Machine Translation Evaluation

2022-04-13 · Chrysoula Zerva, Taisiya Glushkova, Ricardo Rei, André F. T. Martins

Trainable evaluation metrics for machine translation (MT) exhibit strong correlation with human judgements, but they are often hard to interpret and might produce unreliable scores under noisy or out-of-domain data. Rece…

Machine TranslationPredictionTranslationUncertainty Quantification

Lexically Cohesive Neural Machine Translation with Copy Mechanism

2020-10-11 · Vipul Mishra, Chenhui Chu, Yuki Arase

Lexically cohesive translations preserve consistency in word choices in document-level translation. We employ a copy mechanism into a context-aware neural machine translation model to allow copying words from previous tr…

Machine TranslationTranslation