Che, Urdu language processing: A survey, Artif. Bengio, Learning phrase representations using RNN encoder-decoder for statistical machine translation, arXiv:1406.1078. Le, Massive exploration of neural machine translation architectures, arXiv:1703.03906. Sennrich, Regularization techniques for fine-tuning in neural machine translation, arXiv:1707.09920. Bengio, Neural machine translation by jointly learning to align and translate, arXiv:1409.0473. Agirre, An effective approach to unsupervised machine translation, arXiv:1902.01313. Al-Mansoub, Improved Arabic–Chinese machine translation with linguistic input features, Future Internet 11(1) ( 2019) 1–17. Antony, Machine translation approaches and survey for indian languages, Int. Khalid, Urdu language translator using deep neural network, Indian J. Youssif, Sentiment analysis for movies reviews dataset using deep learning models, Int. (INMIC) (IEEE, Lahore, Pakistan, 2017), pp. ul Hussain, Sequence to sequence networks for roman-urdu to urdu transliteration, 2017 Int. Jain, English to sanskrit transliteration: An effective approach to design natural language translation tool, Int. Our qualitative experimental evaluation shows that our models generate coherent transliterations which are grammatically and logically correct. Overall, attention-based model gives state-of-the-art performance with the benchmark of 70 BLEU score. To this end, we present (i) the first ever Roman-Urdu to Urdu parallel corpus of 1.1 million sentences, (ii) three state of the art encoder-decoder models, and (iii) a detailed empirical analysis of these three models on the Roman-Urdu to Urdu parallel corpus. Ours is the first attempt to apply the deep neural network-based encoder-decoder using attention mechanism to address the aforementioned problem using Roman-Urdu and Urdu parallel corpus. To the best of our knowledge, none of the modern machine translation approaches has been applied to address the research problem of Urdu machine transliteration.
#English to urdu transliteration manual
This data-driven approach leads to generic and scalable solutions with no reliance on manual hand-crafted features.
Usually, the encoders and decoders are two recurrent neural networks where the decoder is directed to focus on relevant parts of the source language using attention mechanism. Attention-based encoder-decoder models have superseded conventional techniques due to their unmatched performance on many neural machine translation problems.
0 kommentar(er)
