English
Related papers

Related papers: BLEU might be Guilty but References are not Innoce…

200 papers

Text generation has made significant advances in the last few years. Yet, evaluation metrics have lagged behind, as the most popular choices (e.g., BLEU and ROUGE) may correlate poorly with human judgments. We propose BLEURT, a learned…

Computation and Language · Computer Science 2020-05-22 Thibault Sellam , Dipanjan Das , Ankur P. Parikh

There have been several meta-evaluation studies on the correlation between human ratings and offline machine translation (MT) evaluation metrics such as BLEU, chrF2, BertScore and COMET. These metrics have been used to evaluate simultaneous…

Computation and Language · Computer Science 2023-06-02 Dominik Macháček , Ondřej Bojar , Raj Dabre

Re-speaking is a mechanism for obtaining high quality subtitles for use in live broadcast and other public events. Because it relies on humans performing the actual re-speaking, the task of estimating the quality of the results is…

Computation and Language · Computer Science 2016-01-13 Krzysztof Wołk , Danijel Koržinek

Since the 1950s, machine translation (MT) has become one of the important tasks of AI and development, and has experienced several different periods and stages of development, including rule-based methods, statistical methods, and recently…

Computation and Language · Computer Science 2022-02-23 Lifeng Han

Measuring the performance of natural language processing models is challenging. Traditionally used metrics, such as BLEU and ROUGE, originally devised for machine translation and summarization, have been shown to suffer from low correlation…

Computation and Language · Computer Science 2022-04-26 Kathrin Blagec , Georg Dorffner , Milad Moradi , Simon Ott , Matthias Samwald

Machine-translated benchmarks are widely used to assess the multilingual capabilities of large language models (LLMs), yet translation errors in these benchmarks remain underexplored, raising concerns about the reliability and comparability…

Computation and Language · Computer Science 2026-05-26 Klaudia-Doris Thellmann , Bernhard Stadler , Michael Färber , Jens Lehmann

Neural metrics for machine translation evaluation, such as COMET, exhibit significant improvements in their correlation with human judgments, as compared to traditional metrics based on lexical overlap, such as BLEU. Yet, neural metrics…

Computation and Language · Computer Science 2023-05-22 Ricardo Rei , Nuno M. Guerreiro , Marcos Treviso , Luisa Coheur , Alon Lavie , André F. T. Martins

Previous work suggests that performance of cross-lingual information retrieval correlates highly with the quality of Machine Translation. However, there may be a threshold beyond which improving query translation quality yields little or no…

Computation and Language · Computer Science 2023-02-02 Bryan Zhang , Amita Misra

Starting from the 1950s, Machine Translation (MT) was challenged by different scientific solutions, which included rule-based methods, example-based and statistical models (SMT), to hybrid models, and very recent years the neural models…

Computation and Language · Computer Science 2025-08-07 Lifeng Han , Serge Gladkoff

Existing metrics for evaluating the quality of automatically generated questions such as BLEU, ROUGE, BERTScore, and BLEURT compare the reference and predicted questions, providing a high score when there is a considerable lexical overlap…

Computation and Language · Computer Science 2023-05-29 Alireza Mohammadshahi , Thomas Scialom , Majid Yazdani , Pouya Yanki , Angela Fan , James Henderson , Marzieh Saeidi

The translation of pronouns presents a special challenge to machine translation to this day, since it often requires context outside the current sentence. Recent work on models that have access to information across sentence boundaries has…

Computation and Language · Computer Science 2019-03-07 Mathias Müller , Annette Rios , Elena Voita , Rico Sennrich

The widely-used automatic evaluation metrics cannot adequately reflect the fluency of the translations. The n-gram-based metrics, like BLEU, limit the maximum length of matched fragments to n and cannot catch the matched fragments longer…

Computation and Language · Computer Science 2016-11-07 Hui Yu , Xiaofeng Wu , Wenbin Jiang , Qun Liu , Shouxun Lin

We propose iteratively prompting a large language model to self-correct a translation, with inspiration from their strong language understanding and translation capability as well as a human-like translation approach. Interestingly,…

Computation and Language · Computer Science 2024-05-03 Pinzhen Chen , Zhicheng Guo , Barry Haddow , Kenneth Heafield

Large language models have demonstrated parallel and even superior translation performance compared to neural machine translation (NMT) systems. However, existing comparative studies between them mainly rely on automated metrics, raising…

Computation and Language · Computer Science 2024-10-15 Zhaokun Jiang , Qianxi Lv , Ziyin Zhang , Lei Lei

The goal of translation, be it by human or by machine, is, given some text in a source language, to produce text in a target language that simultaneously 1) preserves the meaning of the source text and 2) achieves natural expression in the…

Computation and Language · Computer Science 2025-08-08 Gergely Flamich , David Vilar , Jan-Thorsten Peter , Markus Freitag

Despite the recent success of automatic metrics for assessing translation quality, their application in evaluating the quality of machine-translated chats has been limited. Unlike more structured texts like news, chat conversations are…

Computation and Language · Computer Science 2024-03-14 Sweta Agrawal , Amin Farajian , Patrick Fernandes , Ricardo Rei , André F. T. Martins

Several code summarization techniques have been proposed in the literature to automatically document a code snippet or a function. Ideally, software developers should be involved in assessing the quality of the generated summaries. However,…

Software Engineering · Computer Science 2023-12-27 Antonio Mastropaolo , Matteo Ciniselli , Massimiliano Di Penta , Gabriele Bavota

Despite increasing instances of machine translation (MT) systems including contextual information, the evidence for translation quality improvement is sparse, especially for discourse phenomena. Popular metrics like BLEU are not expressive…

Computation and Language · Computer Science 2020-05-01 Prathyusha Jwalapuram , Barbara Rychalska , Shafiq Joty , Dominika Basaj

Learned metrics such as BLEURT have in recent years become widely employed to evaluate the quality of machine translation systems. Training such metrics requires data which can be expensive and difficult to acquire, particularly for…

Computation and Language · Computer Science 2023-02-08 Amirkeivan Mohtashami , Mauro Verzetti , Paul K. Rubenstein

We frame the task of machine translation evaluation as one of scoring machine translation output with a sequence-to-sequence paraphraser, conditioned on a human reference. We propose training the paraphraser as a multilingual NMT system,…

Computation and Language · Computer Science 2020-10-29 Brian Thompson , Matt Post