Communication between people with disabilities and people who do not understand sign language is a growing social need and can be a tedious task.One of the main functions of sign language is to communicate with each o...Communication between people with disabilities and people who do not understand sign language is a growing social need and can be a tedious task.One of the main functions of sign language is to communicate with each other through hand gestures.Recognition of hand gestures has become an important challenge for the recognition of sign language.There are many existing models that can produce a good accuracy,but if the model test with rotated or translated images,they may face some difficulties to make good performance accuracy.To resolve these challenges of hand gesture recognition,we proposed a Rotation,Translation and Scale-invariant sign word recognition system using a convolu-tional neural network(CNN).We have followed three steps in our work:rotated,translated and scaled(RTS)version dataset generation,gesture segmentation,and sign word classification.Firstly,we have enlarged a benchmark dataset of 20 sign words by making different amounts of Rotation,Translation and Scale of the ori-ginal images to create the RTS version dataset.Then we have applied the gesture segmentation technique.The segmentation consists of three levels,i)Otsu Thresholding with YCbCr,ii)Morphological analysis:dilation through opening morphology and iii)Watershed algorithm.Finally,our designed CNN model has been trained to classify the hand gesture as well as the sign word.Our model has been evaluated using the twenty sign word dataset,five sign word dataset and the RTS version of these datasets.We achieved 99.30%accuracy from the twenty sign word dataset evaluation,99.10%accuracy from the RTS version of the twenty sign word evolution,100%accuracy from thefive sign word dataset evaluation,and 98.00%accuracy from the RTS versionfive sign word dataset evolution.Furthermore,the influence of our model exists in competitive results with state-of-the-art methods in sign word recognition.展开更多
In the context of globalization,zero translation words are more and more frequently used in news discourse.This article aims to explore the reasons for the frequent use of zero translation words in news discourse and ...In the context of globalization,zero translation words are more and more frequently used in news discourse.This article aims to explore the reasons for the frequent use of zero translation words in news discourse and their impact on news discourse from the perspectives of translation studies and journalism and communication studies.展开更多
This paper explores the translation strategies for Chinese reduplication to English from the perspective of Skopos theory. Drawing on previous research on the semantic functions of reduplication, the paper analyzes th...This paper explores the translation strategies for Chinese reduplication to English from the perspective of Skopos theory. Drawing on previous research on the semantic functions of reduplication, the paper analyzes the three main types of semantic changes in Chinese reduplicated words: intensification of meaning, moderation of meaning, and addition of meaning. The paper then proposes different translation strategies for Chinese reduplication, including same-word repetition, near-synonym repetition, “have a try” form, “noun(pl.) + of” form, and “all”, “each”, and “every” pattern. Finally, the paper emphasizes the importance of understanding the intended communicative function of the reduplicated words and the need for flexible handling in order to achieve a natural translation with better readability.展开更多
This paper deals with the translation strategies of Chinese Culture-Loaded Words from the perspective of adaptation theory.It is based on the translation text of the sixth episode“Silk Road”and the seventh episode“...This paper deals with the translation strategies of Chinese Culture-Loaded Words from the perspective of adaptation theory.It is based on the translation text of the sixth episode“Silk Road”and the seventh episode“Dunhuang”of the documentary Hexi Corridor.Many words with Chinese cultural connotations appear in the subtitles of this documentary.This paper will be divided into four parts.The first part and the second part deal with the basic theories,i.e.,definition of Chinese Culture-Loaded Words and of adaptation theory.The original text is analysed in the third part.This part deals with the background and specifics of the language of the documentary film Hexi Corridor.The fourth part deals with the difficulties encountered by the author in translation practice and the corresponding solutions adopted by the author.The translation difficulties are solved by five translation methods,namely transliteration,loan translation,substitution,interpretation,and adaptation.展开更多
As a special kind of vocabularies originated from the network language,the network hot words are the manifcstation of the diversification of thec nctwork cra as well as of people's social consciousncss,To improve ...As a special kind of vocabularies originated from the network language,the network hot words are the manifcstation of the diversification of thec nctwork cra as well as of people's social consciousncss,To improve the translation quality of Chinese network hot words is not only conducive to promoting the Chinese network culure,but also an important way for foreigner to better understand China.This paper starts from the cases of network hot words translation,making the specific analysis of those words and the relationship among the translator,original writer and target readers.It also analyzes the factors that limit the translator's subjectivity and the translation skills of the network hot words,aiming at further clarifying the translator's subjectivity in the translation of network hot words.Through this research,this paper expectes to have a positive impact on the translation of Chinese network hot words and the promotion of Chinese culture.展开更多
Culture-loaded words refer to expressions and idioms that carry typically culture messages. The peculiarity of one culture cannot be understood or accepted by readers from another culture. The uniqueness very likely m...Culture-loaded words refer to expressions and idioms that carry typically culture messages. The peculiarity of one culture cannot be understood or accepted by readers from another culture. The uniqueness very likely makes misunderstanding and may lead to cultural vacancy in other cultures. Due to the culture differences between Chinese and English, it is hard for a translator to achieve complete equivalence at the level of word. This paper discusses the translation approaches of Chinese cultureloaded words in literary works.展开更多
Hunan Province is rich in red tourism resources, and many scenic spots in the region proudly echo the glory of China's revolutionary history. Publicity materials of red tourism in Hunan Province play the role of p...Hunan Province is rich in red tourism resources, and many scenic spots in the region proudly echo the glory of China's revolutionary history. Publicity materials of red tourism in Hunan Province play the role of publicizing and promoting historical sites and places linked with China's revolutionary history. However, at present the C-E translation of publicity materials of red tourism in Hunan province is far from satisfaction. Reasonable application of eco-translatology in C-E translation of publicity materials of red tourism in Hunan Province will allow the translator to enjoy a much greater degree of flexibility in translating and produce appropriate translation which produce functionally the same effect on the target readers as the original on the readers.展开更多
The correct translation of the Confucian classics is based on the correct comprehension of the culture-loaded words. Therefore, this paper aims to analyze the changing meanings of these words, then find out the ways t...The correct translation of the Confucian classics is based on the correct comprehension of the culture-loaded words. Therefore, this paper aims to analyze the changing meanings of these words, then find out the ways to determine their meanings and at last point out the principle, strategies and methods of better translating these words through discussing the translation purpose and the philosophical nature of the Confucian classics.展开更多
Political words are closely related to the current situations and affairs of China, which is often dependent on China's culture and history. Therefore it is not uncommon that there are some words with background k...Political words are closely related to the current situations and affairs of China, which is often dependent on China's culture and history. Therefore it is not uncommon that there are some words with background knowledge known to the source language readers, but unknown to the target language readers. Literal translation plus explanation is particularly useful in translating these words with particular background and cultural connotations.展开更多
As you can see from the title,we try to provide a brief analysis of ambiguity of words' meaning in translation practice,namely,what is ambiguity of a meaning of a word and how it is caused,and how it affects trans...As you can see from the title,we try to provide a brief analysis of ambiguity of words' meaning in translation practice,namely,what is ambiguity of a meaning of a word and how it is caused,and how it affects translation.What effective methods are available to help us achieve a successful translation? Although a perfect solution for the problems presented by the ambiguity of words' meaning is difficult to find,we try to do what it can to contribute to the solution and draw people's attention to those problems.展开更多
The reduplicative Chinese words in type AABB is a very special form in Chinese language, which is worth researching and analyzing. Through plenty of examples cited in the translation from Chinese to English by the tra...The reduplicative Chinese words in type AABB is a very special form in Chinese language, which is worth researching and analyzing. Through plenty of examples cited in the translation from Chinese to English by the translator Zhang Pei-ji in the four volumes of his translation works, the writer analyzes the phenomenon of translating AABB reduplicative words through examples collected manually in order to summarize the basic rules and principles in doing translation like this. The paper might be useful and helpful in researching translation and Chinese.展开更多
Word conversion means to change the original syntactical functions and morphological features of a word that help to determine a part of speech.In translation it is a small but very important part.This paper is going ...Word conversion means to change the original syntactical functions and morphological features of a word that help to determine a part of speech.In translation it is a small but very important part.This paper is going to focus on its importance in teaching translation through an experiment.Through this experiment it is hoped in teaching translation word conversion devices should be pay great attention.展开更多
Tang poetry is a shining pearl in the history of Chinese literature.C-E translation of Tang poetry is regarded as a very complex and hard task because of its special style and form,concise diction and profound artisti...Tang poetry is a shining pearl in the history of Chinese literature.C-E translation of Tang poetry is regarded as a very complex and hard task because of its special style and form,concise diction and profound artistic conception.Eco-translatology provides a new perspective for the study on C-E translation of Tang poetry.Based on analysis of some practical examples,this paper discusses some C-E translation methods of tang poetry from the perspective of eco-translatology,namely,adaptive transformation from linguistic,cultural and communicative dimensions.展开更多
Translation is not only the process of transforming langue form, but also the process of interacting one thinking means and concept with another. Moreover, so as to ensure accuracy of translation, one needs to compreh...Translation is not only the process of transforming langue form, but also the process of interacting one thinking means and concept with another. Moreover, so as to ensure accuracy of translation, one needs to comprehend the sense of words in the source language correctly, and take appropriate approach to resolve the differences between Chinese and English through analyzing the causes. Therefore, this paper will study the differences of sense of words between English and Chinese in translation.展开更多
This paper aims to analyze the cultural connotations of color words. To successfully translate the expressions relating to colors form Chinese to English or English to Chinese, it is a key step to master the cultural ...This paper aims to analyze the cultural connotations of color words. To successfully translate the expressions relating to colors form Chinese to English or English to Chinese, it is a key step to master the cultural connotations of Chinese and English color words. By comparing the differences of the corresponding color words between Chinese and English, three basic translating methods are generalized.展开更多
Chinese four-character idioms loaded with color words are the typical symbol of the Chinese culture and their transition is important to Chinese-English dictionaries.The quality of the dictionary and users' unders...Chinese four-character idioms loaded with color words are the typical symbol of the Chinese culture and their transition is important to Chinese-English dictionaries.The quality of the dictionary and users' understanding are affected by the correctness and appropriateness of their translation.This paper mainly focuses on the translation of four-character Chinese idioms with color words in New Century Chinese-English Dictionary.The research shows that there are three strategies for Chinese fourcharacter idioms loaded with color words in the dictionaries:literal translation,free translation and the integration of literal translation and annotative translation.展开更多
Retelling extraction is an important branch of Natural Language Processing(NLP),and high-quality retelling resources are very helpful to improve the performance of machine translation.However,traditional methods based...Retelling extraction is an important branch of Natural Language Processing(NLP),and high-quality retelling resources are very helpful to improve the performance of machine translation.However,traditional methods based on the bilingual parallel corpus often ignore the document background in the process of retelling acquisition and application.In order to solve this problem,we introduce topic model information into the translation mode and propose a topic-based statistical machine translation method to improve the translation performance.In this method,Probabilistic Latent Semantic Analysis(PLSA)is used to obtains the co-occurrence relationship between words and documents by the hybrid matrix decomposition.Then we design a decoder to simplify the decoding process.Experiments show that the proposed method can effectively improve the accuracy of translation.展开更多
The translation of Chinese ancient poems has always been the direction of many translators at home and abroad,and the translation of color words has gradually become the object of study.However,due to the difference b...The translation of Chinese ancient poems has always been the direction of many translators at home and abroad,and the translation of color words has gradually become the object of study.However,due to the difference between translation theory and perspective,there are many controversial translations.Based on the theory of "functional equivalence" proposed by American translation theorist Eugene Nida,this paper analyzes the concrete translation of Chinese ancient poems,and aims to explore how to translate the color words in ancient poems in the best way,And summed up the specific and practical translation methods.展开更多
English to Urdu machine translation is still in its beginning and lacks simple translation methods to provide motivating and adequate English to Urdu translation.In order tomake knowledge available to the masses,there...English to Urdu machine translation is still in its beginning and lacks simple translation methods to provide motivating and adequate English to Urdu translation.In order tomake knowledge available to the masses,there should be mechanisms and tools in place to make things understandable by translating from source language to target language in an automated fashion.Machine translation has achieved this goal with encouraging results.When decoding the source text into the target language,the translator checks all the characteristics of the text.To achieve machine translation,rule-based,computational,hybrid and neural machine translation approaches have been proposed to automate the work.In this research work,a neural machine translation approach is employed to translate English text into Urdu.Long Short Term Short Model(LSTM)Encoder Decoder is used to translate English to Urdu.The various steps required to perform translation tasks include preprocessing,tokenization,grammar and sentence structure analysis,word embeddings,training data preparation,encoder-decoder models,and output text generation.The results show that the model used in the research work shows better performance in translation.The results were evaluated using bilingual research metrics and showed that the test and training data yielded the highest score sequences with an effective length of ten(10).展开更多
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 perfo...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.展开更多
基金This work was supported by the Competitive Research Fund of The University of Aizu,Japan.
文摘Communication between people with disabilities and people who do not understand sign language is a growing social need and can be a tedious task.One of the main functions of sign language is to communicate with each other through hand gestures.Recognition of hand gestures has become an important challenge for the recognition of sign language.There are many existing models that can produce a good accuracy,but if the model test with rotated or translated images,they may face some difficulties to make good performance accuracy.To resolve these challenges of hand gesture recognition,we proposed a Rotation,Translation and Scale-invariant sign word recognition system using a convolu-tional neural network(CNN).We have followed three steps in our work:rotated,translated and scaled(RTS)version dataset generation,gesture segmentation,and sign word classification.Firstly,we have enlarged a benchmark dataset of 20 sign words by making different amounts of Rotation,Translation and Scale of the ori-ginal images to create the RTS version dataset.Then we have applied the gesture segmentation technique.The segmentation consists of three levels,i)Otsu Thresholding with YCbCr,ii)Morphological analysis:dilation through opening morphology and iii)Watershed algorithm.Finally,our designed CNN model has been trained to classify the hand gesture as well as the sign word.Our model has been evaluated using the twenty sign word dataset,five sign word dataset and the RTS version of these datasets.We achieved 99.30%accuracy from the twenty sign word dataset evaluation,99.10%accuracy from the RTS version of the twenty sign word evolution,100%accuracy from thefive sign word dataset evaluation,and 98.00%accuracy from the RTS versionfive sign word dataset evolution.Furthermore,the influence of our model exists in competitive results with state-of-the-art methods in sign word recognition.
文摘In the context of globalization,zero translation words are more and more frequently used in news discourse.This article aims to explore the reasons for the frequent use of zero translation words in news discourse and their impact on news discourse from the perspectives of translation studies and journalism and communication studies.
文摘This paper explores the translation strategies for Chinese reduplication to English from the perspective of Skopos theory. Drawing on previous research on the semantic functions of reduplication, the paper analyzes the three main types of semantic changes in Chinese reduplicated words: intensification of meaning, moderation of meaning, and addition of meaning. The paper then proposes different translation strategies for Chinese reduplication, including same-word repetition, near-synonym repetition, “have a try” form, “noun(pl.) + of” form, and “all”, “each”, and “every” pattern. Finally, the paper emphasizes the importance of understanding the intended communicative function of the reduplicated words and the need for flexible handling in order to achieve a natural translation with better readability.
基金Research Startup Project for Doctors at the School of Foreign Languages,University of Shanghai for Science and Technology(Fund Project No.:1F-21-305-101).
文摘This paper deals with the translation strategies of Chinese Culture-Loaded Words from the perspective of adaptation theory.It is based on the translation text of the sixth episode“Silk Road”and the seventh episode“Dunhuang”of the documentary Hexi Corridor.Many words with Chinese cultural connotations appear in the subtitles of this documentary.This paper will be divided into four parts.The first part and the second part deal with the basic theories,i.e.,definition of Chinese Culture-Loaded Words and of adaptation theory.The original text is analysed in the third part.This part deals with the background and specifics of the language of the documentary film Hexi Corridor.The fourth part deals with the difficulties encountered by the author in translation practice and the corresponding solutions adopted by the author.The translation difficulties are solved by five translation methods,namely transliteration,loan translation,substitution,interpretation,and adaptation.
文摘As a special kind of vocabularies originated from the network language,the network hot words are the manifcstation of the diversification of thec nctwork cra as well as of people's social consciousncss,To improve the translation quality of Chinese network hot words is not only conducive to promoting the Chinese network culure,but also an important way for foreigner to better understand China.This paper starts from the cases of network hot words translation,making the specific analysis of those words and the relationship among the translator,original writer and target readers.It also analyzes the factors that limit the translator's subjectivity and the translation skills of the network hot words,aiming at further clarifying the translator's subjectivity in the translation of network hot words.Through this research,this paper expectes to have a positive impact on the translation of Chinese network hot words and the promotion of Chinese culture.
文摘Culture-loaded words refer to expressions and idioms that carry typically culture messages. The peculiarity of one culture cannot be understood or accepted by readers from another culture. The uniqueness very likely makes misunderstanding and may lead to cultural vacancy in other cultures. Due to the culture differences between Chinese and English, it is hard for a translator to achieve complete equivalence at the level of word. This paper discusses the translation approaches of Chinese cultureloaded words in literary works.
文摘Hunan Province is rich in red tourism resources, and many scenic spots in the region proudly echo the glory of China's revolutionary history. Publicity materials of red tourism in Hunan Province play the role of publicizing and promoting historical sites and places linked with China's revolutionary history. However, at present the C-E translation of publicity materials of red tourism in Hunan province is far from satisfaction. Reasonable application of eco-translatology in C-E translation of publicity materials of red tourism in Hunan Province will allow the translator to enjoy a much greater degree of flexibility in translating and produce appropriate translation which produce functionally the same effect on the target readers as the original on the readers.
文摘The correct translation of the Confucian classics is based on the correct comprehension of the culture-loaded words. Therefore, this paper aims to analyze the changing meanings of these words, then find out the ways to determine their meanings and at last point out the principle, strategies and methods of better translating these words through discussing the translation purpose and the philosophical nature of the Confucian classics.
文摘Political words are closely related to the current situations and affairs of China, which is often dependent on China's culture and history. Therefore it is not uncommon that there are some words with background knowledge known to the source language readers, but unknown to the target language readers. Literal translation plus explanation is particularly useful in translating these words with particular background and cultural connotations.
文摘As you can see from the title,we try to provide a brief analysis of ambiguity of words' meaning in translation practice,namely,what is ambiguity of a meaning of a word and how it is caused,and how it affects translation.What effective methods are available to help us achieve a successful translation? Although a perfect solution for the problems presented by the ambiguity of words' meaning is difficult to find,we try to do what it can to contribute to the solution and draw people's attention to those problems.
文摘The reduplicative Chinese words in type AABB is a very special form in Chinese language, which is worth researching and analyzing. Through plenty of examples cited in the translation from Chinese to English by the translator Zhang Pei-ji in the four volumes of his translation works, the writer analyzes the phenomenon of translating AABB reduplicative words through examples collected manually in order to summarize the basic rules and principles in doing translation like this. The paper might be useful and helpful in researching translation and Chinese.
文摘Word conversion means to change the original syntactical functions and morphological features of a word that help to determine a part of speech.In translation it is a small but very important part.This paper is going to focus on its importance in teaching translation through an experiment.Through this experiment it is hoped in teaching translation word conversion devices should be pay great attention.
文摘Tang poetry is a shining pearl in the history of Chinese literature.C-E translation of Tang poetry is regarded as a very complex and hard task because of its special style and form,concise diction and profound artistic conception.Eco-translatology provides a new perspective for the study on C-E translation of Tang poetry.Based on analysis of some practical examples,this paper discusses some C-E translation methods of tang poetry from the perspective of eco-translatology,namely,adaptive transformation from linguistic,cultural and communicative dimensions.
文摘Translation is not only the process of transforming langue form, but also the process of interacting one thinking means and concept with another. Moreover, so as to ensure accuracy of translation, one needs to comprehend the sense of words in the source language correctly, and take appropriate approach to resolve the differences between Chinese and English through analyzing the causes. Therefore, this paper will study the differences of sense of words between English and Chinese in translation.
文摘This paper aims to analyze the cultural connotations of color words. To successfully translate the expressions relating to colors form Chinese to English or English to Chinese, it is a key step to master the cultural connotations of Chinese and English color words. By comparing the differences of the corresponding color words between Chinese and English, three basic translating methods are generalized.
文摘Chinese four-character idioms loaded with color words are the typical symbol of the Chinese culture and their transition is important to Chinese-English dictionaries.The quality of the dictionary and users' understanding are affected by the correctness and appropriateness of their translation.This paper mainly focuses on the translation of four-character Chinese idioms with color words in New Century Chinese-English Dictionary.The research shows that there are three strategies for Chinese fourcharacter idioms loaded with color words in the dictionaries:literal translation,free translation and the integration of literal translation and annotative translation.
基金supported by National Social Science Fund of China(Youth Program):“A Study of Acceptability of Chinese Government Public Signs in the New Era and the Countermeasures of the English Translation”(No.:13CYY010)the Subject Construction and Management Project of Zhejiang Gongshang University:“Research on the Organic Integration Path of Constructing Ideological and Political Training and Design of Mixed Teaching Platform during Epidemic Period”(No.:XKJS2020007)Ministry of Education IndustryUniversity Cooperative Education Program:“Research on the Construction of Cross-border Logistics Marketing Bilingual Course Integration”(NO.:202102494002).
文摘Retelling extraction is an important branch of Natural Language Processing(NLP),and high-quality retelling resources are very helpful to improve the performance of machine translation.However,traditional methods based on the bilingual parallel corpus often ignore the document background in the process of retelling acquisition and application.In order to solve this problem,we introduce topic model information into the translation mode and propose a topic-based statistical machine translation method to improve the translation performance.In this method,Probabilistic Latent Semantic Analysis(PLSA)is used to obtains the co-occurrence relationship between words and documents by the hybrid matrix decomposition.Then we design a decoder to simplify the decoding process.Experiments show that the proposed method can effectively improve the accuracy of translation.
文摘The translation of Chinese ancient poems has always been the direction of many translators at home and abroad,and the translation of color words has gradually become the object of study.However,due to the difference between translation theory and perspective,there are many controversial translations.Based on the theory of "functional equivalence" proposed by American translation theorist Eugene Nida,this paper analyzes the concrete translation of Chinese ancient poems,and aims to explore how to translate the color words in ancient poems in the best way,And summed up the specific and practical translation methods.
基金King Saud University through Researchers Supporting Project number(RSP-2021/387),King Saud University,Riyadh,Saudi Arabia.
文摘English to Urdu machine translation is still in its beginning and lacks simple translation methods to provide motivating and adequate English to Urdu translation.In order tomake knowledge available to the masses,there should be mechanisms and tools in place to make things understandable by translating from source language to target language in an automated fashion.Machine translation has achieved this goal with encouraging results.When decoding the source text into the target language,the translator checks all the characteristics of the text.To achieve machine translation,rule-based,computational,hybrid and neural machine translation approaches have been proposed to automate the work.In this research work,a neural machine translation approach is employed to translate English text into Urdu.Long Short Term Short Model(LSTM)Encoder Decoder is used to translate English to Urdu.The various steps required to perform translation tasks include preprocessing,tokenization,grammar and sentence structure analysis,word embeddings,training data preparation,encoder-decoder models,and output text generation.The results show that the model used in the research work shows better performance in translation.The results were evaluated using bilingual research metrics and showed that the test and training data yielded the highest score sequences with an effective length of ten(10).
基金This work was supported by the Institute for Big Data Analytics and Artificial Intelligence(IBDAAI),Universiti Teknologi Mara,Shah Alam,Selangor.Malaysia.
文摘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.
