Ayato Kuwana
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Ayato Kuwana has a total of 3 co-authors. Here are the top co-authors by number of shared publications:
- Incheon Paik
The University of Aizu
2 shared publications - Ranto Sawai
School of Computer Science and Engineering, The University of Aizu, Fukushima 965-8580, Japan
2 shared publications - Atsushi Oba
Graduate Department of Computer Science and Information Systems, University of Aizu, Tsuruga, Fukushima 965-8580, Japan
1 shared publication
Latest Publications
- Open Access
- 10 December 2021
- Published by MDPI AG in Electronics
- Vol. 10 (24) , 3082
Sentence Augmentation for Language Translation Using GPT-2
Data augmentation has recently become an important method for improving performance in deep learning. It is also a significant issue in machine translation, and various innovations such as back-translation and noising have been made. In particular, current state-of-the-art model architectures such as BERT-fused or efficient data generation using the GPT model provide good inspiration to improve the translation performance. In this study, we propose the generation of additional data for neural machine translation (NMT) using a sentence generator by GPT-2 that produces similar characteristics to the original. BERT-fused architecture and back-translation are employed for the translation architecture. In our experiments, the model produced BLEU scores of 27.50 for tatoebaEn-Ja, 30.14 for WMT14En-De, and 24.12 for WMT18En-Ch.
- 10 December 2021
- Published by MDPI AG in Electronics
- Vol. 10 (24) , 3082
Open AccessSentence Augmentation for Language Translation Using GPT-2
Data augmentation has recently become an important method for improving performance in deep learning. It is also a significant issue in machine translation, and various innovations such as back-translation and noising have been made. In particular, current state-of-the-art model architectures such as BERT-fused or efficient data generation using the GPT model provide good inspiration to improve the translation performance. In this study, we propose the generation of additional data for neural machine translation (NMT) using a sentence generator by GPT-2 that produces similar characteristics to the original. BERT-fused architecture and back-translation are employed for the translation architecture. In our experiments, the model produced BLEU scores of 27.50 for tatoebaEn-Ja, 30.14 for WMT14En-De, and 24.12 for WMT18En-Ch.
- Open Access
- 29 October 2021
- Published by MDPI AG in Electronics
- Vol. 10 (21) , 2656
Automatic Taxonomy Classification by Pretrained Language Model
In recent years, automatic ontology generation has received significant attention in information science as a means of systemizing vast amounts of online data. As our initial attempt of ontology generation with a neural network, we proposed a recurrent neural network-based method. However, updating the architecture is possible because of the development in natural language processing (NLP). By contrast, the transfer learning of language models trained by a large, unlabeled corpus has yielded a breakthrough in NLP. Inspired by these achievements, we propose a novel workflow for ontology generation comprising two-stage learning. Our results showed that our best method improved accuracy by over 12.5%. As an application example, we applied our model to the Stanford Question Answering Dataset to show ontology generation in a real field. The results showed that our model can generate a good ontology, with some exceptions in the real field, indicating future research directions to improve the quality.
- 29 October 2021
- Published by MDPI AG in Electronics
- Vol. 10 (21) , 2656
Open AccessAutomatic Taxonomy Classification by Pretrained Language Model
In recent years, automatic ontology generation has received significant attention in information science as a means of systemizing vast amounts of online data. As our initial attempt of ontology generation with a neural network, we proposed a recurrent neural network-based method. However, updating the architecture is possible because of the development in natural language processing (NLP). By contrast, the transfer learning of language models trained by a large, unlabeled corpus has yielded a breakthrough in NLP. Inspired by these achievements, we propose a novel workflow for ontology generation comprising two-stage learning. Our results showed that our best method improved accuracy by over 12.5%. As an application example, we applied our model to the Stanford Question Answering Dataset to show ontology generation in a real field. The results showed that our model can generate a good ontology, with some exceptions in the real field, indicating future research directions to improve the quality.