| Journal: | Computación y sistemas |
| Database: | |
| System number: | 000560747 |
| ISSN: | 1405-5546 |
| Authors: | Laskar, Sahinur Rahman1 Manna, Riyanka2 Pakray, Partha1 Bandyopadhyay, Sivaji1 |
| Institutions: | 1National Institute of Technology Silchar, Department of Computer Science and Engineering, India 2Adamas University, Department of Computer Science and Engineering, India |
| Year: | 2022 |
| Season: | Oct-Dic |
| Volumen: | 26 |
| Number: | 4 |
| Pages: | 1669-1687 |
| Country: | México |
| Language: | Inglés |
| English abstract | Machine translation deals with automatic translation from one natural language to another. Neural machine translation is a widely accepted technique of the corpus-based machine translation approach. However, an adequate amount of training data is required, and there is a need for the domain-wise parallel corpus to improve translational performance that shows translational coverages in various domains. In this work, a domain-specific parallel corpus is prepared that includes different domain coverages, namely, Agriculture, Government Office, Judiciary, Social Media, Tourism, COVID-19, Sports, and Literature domains for low-resource English-Assamese pair translation. Moreover, we have tackled data scarcity and word-order divergence problems via data augmentation and prior alignment concept. Also, we have contributed Assamese pretrained LM, Assamese word-embeddings by utilizing Assamese monolingual data, and a bilingual dictionary-based post-processing step to enhance transformer-based neural machine translation. We have achieved state-of-the-art results for both forward (English-to-Assamese) and backward (Assamese-to-English) directions of translation. |
| Keyword: | English-Assamese, Low-resource, Neural machine translation, Parallel corpus, Data augmentation, Prior alignment, Language model |
| Full text: | Texto completo (Ver HTML) Texto completo (Ver PDF) |
