Machine Translation System Using Deep Learning for English to Urdu

Andrabi, Syed Abdul Basit; Wahid, Abdul

doi:10.1155/2022/7873012

Cited by 40 publications

(12 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As far as the shortcomings of the two are concerned, the biggest disadvantage of human translation is that the quality of translation results greatly depends on the translator's translation skills. At the same time, because the translator digests the language to be translated rst and then transforms it into another language he is familiar with, the meaning tendency of the translated content is easily a ected by the translator [4]. In the age when the computer has not been invented, the communication between di erent languages mainly depends on translators to translate works such as characters so that people can understand the local customs and national culture outside different languages.…”

Section: Introductionmentioning

confidence: 99%

The Relationship between Machine Translation and Human Translation under the Influence of Artificial Intelligence Machine Translation

Lihua

2022

Mobile Information Systems

View full text Add to dashboard Cite

Machine translation based on artificial intelligence has many commercial applications, such as Google translation, Baidu translation, and Youdao translation. More artificial intelligence and its translation are still used in all aspects of life. Therefore, we should reexamine its impact on the relationship between human translation and machine translation. Therefore, based on this background, this paper discusses the impact of the development of artificial intelligence machine translation on the relationship between human translation and machine translation. Although the translation accuracy and overall situation of machine translation based on artificial intelligence are similar to that of human translation, the basic algorithm of machine translation is still a program that judges right and wrong through computer code. It cannot simulate the “faithfulness, expressiveness, and elegance” of human translation in combination with social background and human culture. However, for some mechanical operations, such as business translation, scenes with low requirements, such as common vocabulary in daily tourism, can still meet the needs. Therefore, under the influence of artificial intelligence machine translation, the relationship between the two is that machine translation can replace human translation in some aspects, but it cannot replace human translation.

show abstract

Section: Introductionmentioning

confidence: 99%

The Relationship between Machine Translation and Human Translation under the Influence of Artificial Intelligence Machine Translation

Lihua

2022

Mobile Information Systems

View full text Add to dashboard Cite

show abstract

“…In the literature, we can find a few research works attempting to use NNET to translate English to Urdu and vice-versa. Andrabi et al [28] proposed English to Urdu MT that employed an LSTMbased encoder-decoder model. Analysis of the translation showed improvement in translation quality and BLEU score.…”

Section: Urdu-to-english Mtmentioning

confidence: 99%

Neural Machine Translation Models with Attention-Based Dropout Layer

Israr¹,

Khan²,

Tahir³

et al. 2023

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

In bilingual translation, attention-based Neural Machine Translation (NMT) models are used to achieve synchrony between input and output sequences and the notion of alignment. NMT model has obtained state-of-the-art performance for several language pairs. However, there has been little work exploring useful architectures for Urdu-to-English machine translation. We conducted extensive Urdu-to-English translation experiments using Long short-term memory (LSTM)/Bidirectional recurrent neural networks (Bi-RNN)/Statistical recurrent unit (SRU)/Gated recurrent unit (GRU)/Convolutional neural network (CNN) and Transformer. Experimental results show that Bi-RNN and LSTM with attention mechanism trained iteratively, with a scalable data set, make precise predictions on unseen data. The trained models yielded competitive results by achieving 62.6% and 61% accuracy and 49.67 and 47.14 BLEU scores, respectively. From a qualitative perspective, the translation of the test sets was examined manually, and it was observed that trained models tend to produce repetitive output more frequently. The attention score produced by Bi-RNN and LSTM produced clear alignment, while GRU showed incorrect translation for words, poor alignment and lack of a clear structure. Therefore, we considered refining the attention-based models by defining an additional attention-based dropout layer. Attention dropout fixes alignment errors and minimizes translation errors at the word level. After empirical demonstration and comparison with their counterparts, we found improvement in the quality of the resulting translation system and a decrease in the perplexity and over-translation score. The ability of the proposed model was evaluated using Arabic-English and Persian-English datasets as well. We empirically concluded that adding an attention-based dropout layer helps improve GRU, SRU, and Transformer translation and is considerably more efficient in translation quality and speed.

show abstract

“…Urdu Language. Urdu is a popular South Asian language, and about 70 million native speakers and more than 164 million people speak around the world (Andrabi & Wahid, 2022;Rehman et al, 2011). Urdu is the official literary language of Pakistan, spoken and understood in many countries like India, and Bangladesh, and is closely related to Hindi.…”

Section: Preservation Challenges In Low-resource Languagesmentioning

confidence: 99%

Metadata for Efficient Management of Digital News Articles in Multilingual News Archives

Khan,

Alharbi,

Alferaidi

et al. 2023

SAGE Open

View full text Add to dashboard Cite

The digital news preservation and management of low-resource languages are challenging tasks, especially in vast collections. Unique identification of individual digital objects is possible with well-defined attributes to assure efficient management, such as access, retrieval, preservation, usability, and transformability. The metadata element set is required to maximize the available attributes related to the digital objects. To create a comprehensive metadata set that contains all the necessary attributes and data about the digital news objects. It is more challenging and complicated when the archive contains articles from low-resourced and morphologically complex languages like Urdu and Arabic, which is difficult for machines to understand. The study presents challenges in low-resource languages (LRL) and research challenges. This metadata will help to link news articles based on similarity with other news articles stored in the digital news stories archive (DNSA) and ensures accessibility. In this study, we introduced 38 metadata elements set for the digital news stories preservation (DNSP) framework, of which 16 are explicit and 12 are implicit metadata elements. The paper presents how the digital news stories archive (DNSA) is enhanced to a multilingual archive and discusses the digital news stories extractor, which addresses major issues in implementing low-resource languages and facilitates normalized format migration. The extraction results are presented in detail for high-resource languages, that is, English, and low-resource languages (HRL), that is, Urdu and Arabic. The LRL encountered a high error rate during preservation compared to HRL, 10%, and 03%, respectively. The metadata extraction results show that HRL sources support all metadata elements as compared to LRL. The LRL has good support for explicit meta elements and many implicit meta elements with low extraction percentages. The LRL needs a more detailed study for accurate news content extraction and archiving for future access.

show abstract

Machine Translation System Using Deep Learning for English to Urdu

Cited by 40 publications

References 17 publications

The Relationship between Machine Translation and Human Translation under the Influence of Artificial Intelligence Machine Translation

The Relationship between Machine Translation and Human Translation under the Influence of Artificial Intelligence Machine Translation

Neural Machine Translation Models with Attention-Based Dropout Layer

Metadata for Efficient Management of Digital News Articles in Multilingual News Archives

Contact Info

Product

Resources

About