A Comparison of Transformer, Recurrent Neural Networks and SMT in Tamil to Sinhala MT
| Autor: | Ashmari Pramodya, Randil Pushpananda, Ruvan Weerasinghe |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
Network architecture
Machine translation business.industry Computer science Context (language use) 010501 environmental sciences Semantics computer.software_genre 01 natural sciences language.human_language 030507 speech-language pathology & audiology 03 medical and health sciences Recurrent neural network Tamil language Artificial intelligence State (computer science) 0305 other medical science business computer Natural language processing 0105 earth and related environmental sciences Transformer (machine learning model) |
| Zdroj: | 2020 20th International Conference on Advances in ICT for Emerging Regions (ICTer). |
| DOI: | 10.1109/icter51097.2020.9325431 |
| Popis: | Neural Machine Translation (NMT) is currently the most promising approach for machine translation. The attention mechanism is a successful technique in modern Natural Language Processing (NLP), especially in tasks like machine translation. The recently proposed network architecture of the Transformer is based entirely on attention mechanisms and achieves a new state of the art results in neural machine translation, outperforming other sequence-to-sequence models. Although it is successful in a resource-rich setting, its applicability for low-resource language pairs is still debatable. Additionally when the language pair is morphologically rich and also when the corpora is multi-domain, the lack of a large parallel corpus becomes a significant barrier. In this study, we explore different NMT algorithms – Long Short Term Memory (LSTM) and Transformer based NMT, to translate the Tamil to Sinhala language pair. Where we clearly see transformer outperforms LSTM by 2.43 BLEU score for Tamil to Sinhala direction. And this work provides a preliminary comparison of statistical machine translation (SMT) and Neural Machine Translation (NMT) for Tamil to Sinhala in the open domain context. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|