English
Related papers

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

200 papers

We introduce a dataset comprising commercial machine translations, gathered weekly over six years across 12 translation directions. Since human A/B testing is commonly used, we assume commercial systems improve over time, which enables us…

Computation and Language · Computer Science 2024-10-04 Guojun Wu , Shay B. Cohen , Rico Sennrich

Neural machine translation (NMT) models are conventionally trained with token-level negative log-likelihood (NLL), which does not guarantee that the generated translations will be optimized for a selected sequence-level evaluation metric.…

Computation and Language · Computer Science 2021-04-16 Raphael Shu , Kang Min Yoo , Jung-Woo Ha

Quality estimation (QE) is the task of automatically evaluating the quality of translations without human-translated references. Calculating BLEU between the input sentence and round-trip translation (RTT) was once considered as a metric…

Computation and Language · Computer Science 2020-04-30 Jihyung Moon , Hyunchang Cho , Eunjeong L. Park

Recent advances in statistical machine translation via the adoption of neural sequence-to-sequence models empower the end-to-end system to achieve state-of-the-art in many WMT benchmarks. The performance of such machine translation (MT)…

Computation and Language · Computer Science 2018-11-20 Kai Fan , Jiayi Wang , Bo Li , Fengming Zhou , Boxing Chen , Luo Si

Automatic metrics are used as proxies to evaluate abstractive summarization systems when human annotations are too expensive. To be useful, these metrics should be fine-grained, show a high correlation with human annotations, and ideally be…

Computation and Language · Computer Science 2024-10-16 Théo Gigant , Camille Guinaudeau , Marc Decombas , Frédéric Dufaux

Machine translation evaluation is a very important activity in machine translation development. Automatic evaluation metrics proposed in literature are inadequate as they require one or more human reference translations to compare them with…

Computation and Language · Computer Science 2013-11-18 Nisheeth Joshi , Iti Mathur , Hemant Darbari , Ajai Kumar

While a source sentence can be translated in many ways, most machine translation (MT) models are trained with only a single reference. Previous work has shown that using synthetic paraphrases can improve MT. This paper investigates best…

Computation and Language · Computer Science 2025-02-27 Si Wu , John Wieting , David A. Smith

Machine translation has an undesirable propensity to produce "translationese" artifacts, which can lead to higher BLEU scores while being liked less by human raters. Motivated by this, we model translationese and original (i.e. natural)…

Computation and Language · Computer Science 2020-07-13 Parker Riley , Isaac Caswell , Markus Freitag , David Grangier

Human language production exhibits remarkable richness and variation, reflecting diverse communication styles and intents. However, this variation is often overlooked in summarization evaluation. While having multiple reference summaries is…

Computation and Language · Computer Science 2025-09-17 Silvia Casola , Yang Janet Liu , Siyao Peng , Oliver Kraus , Albert Gatt , Barbara Plank

Reproducibility is of utmost concern in machine learning and natural language processing (NLP). In the field of natural language generation (especially machine translation), the seminal paper of Post (2018) has pointed out problems of…

Computation and Language · Computer Science 2022-10-28 Yanran Chen , Jonas Belouadi , Steffen Eger

The high-quality translation results produced by machine translation (MT) systems still pose a huge challenge for automatic evaluation. Current MT evaluation pays the same attention to each sentence component, while the questions of…

Computation and Language · Computer Science 2021-08-02 Runzhe Zhan , Xuebo Liu , Derek F. Wong , Lidia S. Chao

Automated metrics for Machine Translation have made significant progress, with the goal of replacing expensive and time-consuming human evaluations. These metrics are typically assessed by their correlation with human judgments, which…

Computation and Language · Computer Science 2024-12-31 Pius von Däniken , Jan Deriu , Mark Cieliebak

Assessing the performance of interpreting services is a complex task, given the nuanced nature of spoken language translation, the strategies that interpreters apply, and the diverse expectations of users. The complexity of this task become…

Computation and Language · Computer Science 2024-06-17 Xiaoman Wang , Claudio Fantinuoli

Despite significant improvements in enhancing the quality of translation, context-aware machine translation (MT) models underperform in many cases. One of the main reasons is that they fail to utilize the correct features from context when…

Computation and Language · Computer Science 2024-05-01 Huy Hien Vu , Hidetaka Kamigaito , Taro Watanabe

Machine translation (MT) was developed as one of the hottest research topics in the natural language processing (NLP) literature. One important issue in MT is that how to evaluate the MT system reasonably and tell us whether the translation…

Computation and Language · Computer Science 2022-01-25 Lifeng Han

Reference-based metrics such as BLEU and BERTScore are widely used to evaluate question generation (QG). In this study, on QG benchmarks such as SQuAD and HotpotQA, we find that using human-written references cannot guarantee the…

Computation and Language · Computer Science 2024-10-11 Bang Nguyen , Mengxia Yu , Yun Huang , Meng Jiang

In Machine Translation (MT) evaluation, metric performance is assessed based on agreement with human judgments. In recent years, automatic metrics have demonstrated increasingly high levels of agreement with humans. To gain a clearer…

Computation and Language · Computer Science 2025-06-25 Lorenzo Proietti , Stefano Perrella , Roberto Navigli

Statistical machine translation (SMT) is a fast-growing sub-field of computational linguistics. Until now, the most popular automatic metric to measure the quality of SMT is BiLingual Evaluation Understudy (BLEU) score. Lately, SMT along…

Software Engineering · Computer Science 2019-06-13 Ngoc Tran , Hieu Tran , Son Nguyen , Hoan Nguyen , Tien N. Nguyen

In Machine Translation, assessing the quality of a large amount of automatic translations can be challenging. Automatic metrics are not reliable when it comes to high performing systems. In addition, resorting to human evaluators can be…

Computation and Language · Computer Science 2021-05-31 Vânia Mendonça , Ricardo Rei , Luisa Coheur , Alberto Sardinha , Ana Lúcia Santos

Despite advances in open-domain dialogue systems, automatic evaluation of such systems is still a challenging problem. Traditional reference-based metrics such as BLEU are ineffective because there could be many valid responses for a given…

Computation and Language · Computer Science 2019-04-25 Sarik Ghazarian , Johnny Tian-Zheng Wei , Aram Galstyan , Nanyun Peng