Results 41 to 50 of about 4,505,015 (366)
Contrastive Learning for Many-to-many Multilingual Neural Machine Translation [PDF]
Annual Meeting of the Association for Computational Linguistics, 2021 Existing multilingual machine translation approaches mainly focus on English-centric directions, while the non-English directions still lag behind. In this work, we aim to build a many-to-many translation system with an emphasis on the quality of non ...
Xiao Pan +3 more
semanticscholar +1 more source
Conference on Machine Translation, 2023 While large language models have made remarkable advancements in natural language generation, their potential in machine translation, especially when fine-tuned, remains under-explored.
Xuan Zhang +3 more
semanticscholar +1 more source
The Curious Case of Hallucinations in Neural Machine Translation [PDF]
North American Chapter of the Association for Computational Linguistics, 2021 In this work, we study hallucinations in Neural Machine Translation (NMT), which lie at an extreme end on the spectrum of NMT pathologies. Firstly, we connect the phenomenon of hallucinations under source perturbation to the Long-Tail theory of Feldman ...
Vikas Raunak +2 more
semanticscholar +1 more source
Sovremennye Issledovaniâ Socialʹnyh Problem, 2022 The article is devoted to the analysis of the psychological scientific text machine translation (from the English language to the Russian one). On the material of the Russian machine translation of an informational brochure, potential difficulties were ...
Ksenia V. Antaeva, Yulia S. Elagina
doaj +1 more source
Survey of Low-Resource Machine Translation [PDF]
Computational Linguistics, 2021 We present a survey covering the state of the art in low-resource machine translation (MT) research. There are currently around 7,000 languages spoken in the world and almost all language pairs lack significant resources for training machine translation ...
B. Haddow +4 more
semanticscholar +1 more source
Evaluation of English–Slovak Neural and Statistical Machine Translation
Applied Sciences, 2021 This study is focused on the comparison of phrase-based statistical machine translation (SMT) systems and neural machine translation (NMT) systems using automatic metrics for translation quality evaluation for the language pair of English and Slovak.
Lucia Benkova +3 more
doaj +1 more source
Adaptive Nearest Neighbor Machine Translation [PDF]
Annual Meeting of the Association for Computational Linguistics, 2021 kNN-MT, recently proposed by Khandelwal et al. (2020a), successfully combines pre-trained neural machine translation (NMT) model with token-level k-nearest-neighbor (kNN) retrieval to improve the translation accuracy.
Xin Zheng +6 more
semanticscholar +1 more source
Google Translate and DeepL: Breaking taboos in translator training. Observational study and analysis
Ibérica, 2023 In recent decades, when we read about the use of machine translation, we were told that it was not suitable for professional translation. The reason was that machine translation used to produce poor results as long as it was not applied to controlled ...
María-José Varela Salinas, Ruth Burbat
doaj +1 more source
Multi-View Network Representation Learning Algorithm Research
Algorithms, 2019 Network representation learning is a key research field in network data mining. In this paper, we propose a novel multi-view network representation algorithm (MVNR), which embeds multi-scale relations of network vertices into the low dimensional ...
Zhonglin Ye +3 more
doaj +1 more source
Pre-editing English news texts for machine translation into Russian
Исследования языка и современное гуманитарное знание, 2022 The paper discusses the possible advantages of pre-editing English news texts for machine translation into Russian. Pre-editing is defined as a process of adapting source text in order to reach a better quality of machine translation.
Елена Коканова +2 more
doaj +1 more source