T. T. Nguyen
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Research Interests
T. T. Nguyen has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Denis A. Rychkov
Institute of Solid State Chemistry and Mechanochemistry, Kutateladze 18 st., Novosibirsk 630090, Russia
2 shared publications - Sergey G. Arkhipov
Novosibirsk State University, Novosibirsk, Russia; SRF "SKIF", Kol'tsovo, Russia
2 shared publications - Thien Nguyen
Natural Language Processing and Knowledge Discovery Research Group, Faculty of Information Technology, Ton Duc Thang University, Ho Chi Minh City, Vietnam
2 shared publications - Elena Vladimirovna Boldyreva
Sobolev Institute of Geology and Mineralogy SB RAS, pr. Akademika Koptyuga, 3, Novosibirsk, 630090, Russian Federation
1 shared publication - Evgeniy A. Losev
Sobolev Institute of Geology and Mineralogy SB RAS, pr. Akademika Koptyuga, 3, Novosibirsk, 630090, Russian Federation
1 shared publication
Latest Publications
- Open Access
- 3 June 2022
- Published by Hindawi Limited in Computational Intelligence and Neuroscience
- Vol. 2022, 1-8
Heavyweight Statistical Alignment to Guide Neural Translation
Transformer neural models with multihead attentions outperform all existing translation models. Nevertheless, some features of traditional statistical models, such as prior alignment between source and target words, prove useful in training the state-of-the-art Transformer models. It has been reported that lightweight prior alignment can effectively guide a head in the multihead cross-attention sublayer responsible for the alignment of Transformer models. In this work, we make a step further by applying heavyweight prior alignments to guide all heads. Specifically, we use the weight of 0.5 for the alignment cost added to the token cost in formulating the overall cost of training a Transformer model, where the alignment cost is defined as the deviation of the attention probability from the prior alignments. Moreover, we increase the role of prior alignment, computing the attention probability by averaging all heads of the multihead attention sublayer within the penultimate layer of Transformer model. Experimental results on an English-Vietnamese translation task show that our proposed approach helps train superior Transformer-based translation models. Our Transformer model (25.71) outperforms the baseline model (21.34) by the large 4.37 BLEU. Case studies by native speakers on some translation results validate the machine judgment. The results so far encourage the use of heavyweight prior alignments to improve Transformer-based translation models. This work contributes to the literature on the machine translation, especially, for unpopular language pairs. Since the proposal in this work is language-independent, it can be applied to different language pairs, including Slavic languages.
- 3 June 2022
- Published by Hindawi Limited in Computational Intelligence and Neuroscience
- Vol. 2022, 1-8
Open AccessHeavyweight Statistical Alignment to Guide Neural Translation
Transformer neural models with multihead attentions outperform all existing translation models. Nevertheless, some features of traditional statistical models, such as prior alignment between source and target words, prove useful in training the state-of-the-art Transformer models. It has been reported that lightweight prior alignment can effectively guide a head in the multihead cross-attention sublayer responsible for the alignment of Transformer models. In this work, we make a step further by applying heavyweight prior alignments to guide all heads. Specifically, we use the weight of 0.5 for the alignment cost added to the token cost in formulating the overall cost of training a Transformer model, where the alignment cost is defined as the deviation of the attention probability from the prior alignments. Moreover, we increase the role of prior alignment, computing the attention probability by averaging all heads of the multihead attention sublayer within the penultimate layer of Transformer model. Experimental results on an English-Vietnamese translation task show that our proposed approach helps train superior Transformer-based translation models. Our Transformer model (25.71) outperforms the baseline model (21.34) by the large 4.37 BLEU. Case studies by native speakers on some translation results validate the machine judgment. The results so far encourage the use of heavyweight prior alignments to improve Transformer-based translation models. This work contributes to the literature on the machine translation, especially, for unpopular language pairs. Since the proposal in this work is language-independent, it can be applied to different language pairs, including Slavic languages.
- 1 January 2020
- Published by Elsevier in Materials Today: Proceedings
- Vol. 25, 412-415
Simple crystallographic model for anomalous plasticity of L-Leucinium hydrogen maleate crystals
- 1 January 2020
- Published by Elsevier in Materials Today: Proceedings
- Vol. 25, 412-415
Simple crystallographic model for anomalous plasticity of L-Leucinium hydrogen maleate crystals
- 13 March 2019
- Published by International Union of Crystallography (IUCr) in Acta crystallographica Section B, Structural science, crystal engineering and materials
- Vol. 75 (2) , 143-151
A large anisotropic plasticity of L-leucinium hydrogen maleate preserved at cryogenic temperatures
L-Leucinium hydrogen maleate crystals are very plastic at ambient conditions. Here it is shown that this plasticity is preserved at least down to 77 K. The structural changes in the temperature range 293–100 K were followed in order to rationalize the large anisotropic plasticity in this compound. To the best of our knowledge, this is the first reported example of an organic compound remaining so plastic at cryogenic conditions.
- 13 March 2019
- Published by International Union of Crystallography (IUCr) in Acta crystallographica Section B, Structural science, crystal engineering and materials
- Vol. 75 (2) , 143-151
A large anisotropic plasticity of L-leucinium hydrogen maleate preserved at cryogenic temperatures
L-Leucinium hydrogen maleate crystals are very plastic at ambient conditions. Here it is shown that this plasticity is preserved at least down to 77 K. The structural changes in the temperature range 293–100 K were followed in order to rationalize the large anisotropic plasticity in this compound. To the best of our knowledge, this is the first reported example of an organic compound remaining so plastic at cryogenic conditions.