Automated essay scoring(AES)systems have gained significant importance in educational settings,offering a scalable,efficient,and objective method for evaluating student essays.However,developing AES systems for Arabic...Automated essay scoring(AES)systems have gained significant importance in educational settings,offering a scalable,efficient,and objective method for evaluating student essays.However,developing AES systems for Arabic poses distinct challenges due to the language’s complex morphology,diglossia,and the scarcity of annotated datasets.This paper presents a hybrid approach to Arabic AES by combining text-based,vector-based,and embeddingbased similarity measures to improve essay scoring accuracy while minimizing the training data required.Using a large Arabic essay dataset categorized into thematic groups,the study conducted four experiments to evaluate the impact of feature selection,data size,and model performance.Experiment 1 established a baseline using a non-machine learning approach,selecting top-N correlated features to predict essay scores.The subsequent experiments employed 5-fold cross-validation.Experiment 2 showed that combining embedding-based,text-based,and vector-based features in a Random Forest(RF)model achieved an R2 of 88.92%and an accuracy of 83.3%within a 0.5-point tolerance.Experiment 3 further refined the feature selection process,demonstrating that 19 correlated features yielded optimal results,improving R2 to 88.95%.In Experiment 4,an optimal data efficiency training approach was introduced,where training data portions increased from 5%to 50%.The study found that using just 10%of the data achieved near-peak performance,with an R2 of 85.49%,emphasizing an effective trade-off between performance and computational costs.These findings highlight the potential of the hybrid approach for developing scalable Arabic AES systems,especially in low-resource environments,addressing linguistic challenges while ensuring efficient data usage.展开更多
The concept of equivalence,which expresses the relations between the source text and the target text in the translation process,can be defined as finding the closest equivalent of the source text in the target text.In...The concept of equivalence,which expresses the relations between the source text and the target text in the translation process,can be defined as finding the closest equivalent of the source text in the target text.In order for the translated text to have the same taste in the target language,the equivalence between the two languages should be good.Many novels have been translated from English to Arabic.This translation was translated from English to Arabic.Jane Eyre is in the Victorian England.The novel is about love between two people of different classes,underlining the pressures,class distinction,male domination in society.Jane Eyre,who was one of the first novels about women’s freedom and rights,is also one of the most important works of romanticism.The author was inspired by his own life.In this study,language plays in Arabic translation of famous novelist Charlotte Bronte’s Jane Eyre were examined in terms of equivalence.In addition to semantic,syntactic,linguistic,and stylistic dimensions,translation of language games such as proverb,idiom,metaphor,personification,and comparison,which are the main material of a decorated language,is emphasized and their equivalence is interpreted in the light of the theories of translation.The analysis of the selected sample sentences from the novel within the context of translation criticism shows that the translator preserves the form and content of the source text in a significant way and provides a translation equivalent to the original in terms of linguistic,syntactic,and semantic.The Arabic reader seems to be able to understand the language games in English in a similar way in their own language.展开更多
基金funded by Deanship of Graduate studies and Scientific Research at Jouf University under grant No.(DGSSR-2024-02-01264).
文摘Automated essay scoring(AES)systems have gained significant importance in educational settings,offering a scalable,efficient,and objective method for evaluating student essays.However,developing AES systems for Arabic poses distinct challenges due to the language’s complex morphology,diglossia,and the scarcity of annotated datasets.This paper presents a hybrid approach to Arabic AES by combining text-based,vector-based,and embeddingbased similarity measures to improve essay scoring accuracy while minimizing the training data required.Using a large Arabic essay dataset categorized into thematic groups,the study conducted four experiments to evaluate the impact of feature selection,data size,and model performance.Experiment 1 established a baseline using a non-machine learning approach,selecting top-N correlated features to predict essay scores.The subsequent experiments employed 5-fold cross-validation.Experiment 2 showed that combining embedding-based,text-based,and vector-based features in a Random Forest(RF)model achieved an R2 of 88.92%and an accuracy of 83.3%within a 0.5-point tolerance.Experiment 3 further refined the feature selection process,demonstrating that 19 correlated features yielded optimal results,improving R2 to 88.95%.In Experiment 4,an optimal data efficiency training approach was introduced,where training data portions increased from 5%to 50%.The study found that using just 10%of the data achieved near-peak performance,with an R2 of 85.49%,emphasizing an effective trade-off between performance and computational costs.These findings highlight the potential of the hybrid approach for developing scalable Arabic AES systems,especially in low-resource environments,addressing linguistic challenges while ensuring efficient data usage.
文摘The concept of equivalence,which expresses the relations between the source text and the target text in the translation process,can be defined as finding the closest equivalent of the source text in the target text.In order for the translated text to have the same taste in the target language,the equivalence between the two languages should be good.Many novels have been translated from English to Arabic.This translation was translated from English to Arabic.Jane Eyre is in the Victorian England.The novel is about love between two people of different classes,underlining the pressures,class distinction,male domination in society.Jane Eyre,who was one of the first novels about women’s freedom and rights,is also one of the most important works of romanticism.The author was inspired by his own life.In this study,language plays in Arabic translation of famous novelist Charlotte Bronte’s Jane Eyre were examined in terms of equivalence.In addition to semantic,syntactic,linguistic,and stylistic dimensions,translation of language games such as proverb,idiom,metaphor,personification,and comparison,which are the main material of a decorated language,is emphasized and their equivalence is interpreted in the light of the theories of translation.The analysis of the selected sample sentences from the novel within the context of translation criticism shows that the translator preserves the form and content of the source text in a significant way and provides a translation equivalent to the original in terms of linguistic,syntactic,and semantic.The Arabic reader seems to be able to understand the language games in English in a similar way in their own language.
