Abstract Roman Urdu text is most common used language on social networking media in Pakistan and India. It is common knowledge that in roman Urdu text, a large number of phrases and terms are used to represent emotions. In the recent times, Urdu roman has emerged into extra frequent language, for the reason that the people have a choice to... Roman Urdu text is most common used language on social networking media in Pakistan and India. It is common knowledge that in roman Urdu text, a large number of phrases and terms are used to represent emotions. In the recent times, Urdu roman has emerged into extra frequent language, for the reason that the people have a choice to discuss emotions and display their emotions in their personal language. Emotion analysers recognized for extra well-studied languages, identical British, stay not feasible developed for Urdu or roman Urdu, due to their scripted, morphological, and language changes. In this paper, the researcher presents an approach to parse roman Urdu by developing an emotion ontology. Here, a key phase was parsing of roman Urdu text. The proposed motion ontology is used for classification of emotion from roman Urdu text in different categories. Read More Read Less

Abstract Entity Resolution (ER) is the problem of identifying groups of tuples from one or multiple data sources that represent the same real-world entity. This is a crucial stage of data integration processes, which often need to integrate data at query time. This task becomes more challenging in scenarios with dynamic data sources or with a large volume of data. As... Entity Resolution (ER) is the problem of identifying groups of tuples from one or multiple data sources that represent the same real-world entity. This is a crucial stage of data integration processes, which often need to integrate data at query time. This task becomes more challenging in scenarios with dynamic data sources or with a large volume of data. As most ER techniques deal with all tuples at once, new solutions have been proposed to deal with large volumes of data. One possible approach consists in performing the ER process on query results rather than the whole data. In this case, previous results of ER tasks are reused in order to reduce the number of comparisons between pairs of tuples at query time. In a similar way, indexing techniques can also be employed to help the identification of equivalent tuples and to reduce the number of comparisons between pairs of tuples. In this context, this work proposes an indexing technique for incremental Entity Resolution processes. The expected contributions of this work are the specification, the implementation and the evaluation of the proposed indexes. We evaluated the reuse of previous results of the ER process and highlighted its impact. The time spent for storing, accessing and updating the indexes was measured. We concluded that the reuse is more efficient than the reprocessing of tuples comparison. Read More Read Less

Abstract In this paper, we presented an approach that finds the negation in software requirements, and scope of negation. Our approach works at different levels of parsing each level has its own importance. The main phase of our approach is the deep semantic parsing this phase is further divided into three phases that are classification of negation, argument detection and scope... In this paper, we presented an approach that finds the negation in software requirements, and scope of negation. Our approach works at different levels of parsing each level has its own importance. The main phase of our approach is the deep semantic parsing this phase is further divided into three phases that are classification of negation, argument detection and scope detection. First phase classifies the negated sentences into different types of negation as implicit negation, explicit negation, double negation and single negation. Argument detection finds arguments that are negated. The last phase finds the scope of negation the arguments that are actually negated by the negation signal. Experimental works shows that our approach scores better than earlier studies. Read More Read Less