Results 301 to 310 of about 4,831,098 (338)

Stylistic Errors in Translation

Philology & Human, 2022
The article describes the significance and status of stylistic errors in the context of general classification of translation errors. The author stresses that this issue has been studied in the works of Russian and foreign linguists. The topicality of the study is determined by the absence of a unified classification of stylistic errors in translation,
Inna Solovyova, Irina Chudova
openaire   +1 more source

Mind the Gap... or Not? How Translation Errors and Evaluation Details Skew Multilingual Results

arXiv.org
Most current large language models (LLMs) support a wide variety of languages in addition to English, including high-resource languages (e.g. German, Chinese, French), as well as low-resource ones (e.g. Swahili, Telugu).
Jan-Thorsten Peter, David Vilar, Tobias Domhan, Dan Malkin, Markus Freitag   +4 more
semanticscholar   +1 more source

xTower: A Multilingual LLM for Explaining and Correcting Translation Errors

Conference on Empirical Methods in Natural Language Processing
While machine translation (MT) systems are achieving increasingly strong performance on benchmarks, they often produce translations with errors and anomalies.
Marcos V. Treviso, Nuno M. Guerreiro, Sweta Agrawal, Ricardo Rei, José Pombal, Tania Vaz, Helena Wu, Beatriz Silva, Daan van Stigt, Andr'e F. T. Martins   +9 more
semanticscholar   +1 more source

NL2SQL-BUGs: A Benchmark for Detecting Semantic Errors in NL2SQL Translation

Knowledge Discovery and Data Mining
Natural Language to SQL (i.e., NL2SQL) translation is crucial for democratizing database access, but even state-of-the-art models frequently generate semantically incorrect SQL queries, hindering the widespread adoption of these techniques by database ...
Xinyu Liu, Shuyu Shen, Boyan Li, Nan Tang, Yuyu Luo   +4 more
semanticscholar   +1 more source

Translation Errors Significantly Impact Low-Resource Languages in Cross-Lingual Learning

Conference of the European Chapter of the Association for Computational Linguistics
Popular benchmarks (e.g., XNLI) used to evaluate cross-lingual language understanding consist of parallel versions of English evaluation sets in multiple target languages created with the help of professional translators. When creating such parallel data,
Ashish Agrawal, Barah Fazili, P. Jyothi
semanticscholar   +1 more source

Lost in Translation? Translation Errors and Challenges for Fair Assessment of Text-to-Image Models on Multilingual Concepts

North American Chapter of the Association for Computational Linguistics
Benchmarks of the multilingual capabilities of text-to-image (T2I) models compare generated images prompted in a test language to an expected image distribution over a concept set.
Michael Stephen Saxon, Yiran Luo, Sharon Levy, Chitta Baral, Yezhou Yang, W. Wang   +5 more
semanticscholar   +1 more source

Machine translation errors and the translation process: a study across different languages

The Journal of Specialised Translation, 2019
The paper describes an experiment in which two groups of translators annotate Spanish and simplified Chinese MT output of the same English source texts (ST) using an MQM-derived annotation schema.
M. Carl, M. C. T. Báez
semanticscholar   +1 more source

Semantic translation error rate for evaluating translation systems

2007 IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU), 2007
In this paper, we introduce a new metric which we call the semantic translation error rate, or STER, for evaluating the performance of machine translation systems. STER is based on the previously published translation error rate (TER) (Snover et al., 2006) and METEOR (Banerjee and Lavie, 2005) metrics. Specifically, STER extends TER in two ways: first,
Krishna Subramanian 0001, David Stallard, Rohit Prasad, Shirin Saleem, Prem Natarajan   +4 more
openaire   +1 more source

Errors in Translation

1969
During the process of information transfer from gene to protein there are a number of steps which require that this information be transmitted from one type of biological molecule to another. This problem of information transfer and the accompanying problem of recognition is at its most complex in the translation process in which the information ...
openaire   +1 more source

A Self Systematic Review of Translation Error Studies (2000–2025): The Case of Students’ Errors in English–Arabic and Arabic–English Translation

International Journal of Translation and Interpretation Studies
Despite the plethora of empirical studies on students’ translation errors, no systematic reviews (SRs) or meta analyses (MAs) have been conducted in this area.
Reima Al-Jarf
semanticscholar   +1 more source