Figure 2 - uploaded by Sameh Alansary
Content may be subject to copyright.
Source publication
This paper introduces the UNL framework as a collaborative framework that encourages and promotes the participation of linguists and non-linguists in the development of an integral natural language processing workbench. The UNL workbench includes a multitude of user-friendly back-end and front-end applications that facilitate the process of learnin...
Context in source publication
Context 1
... five rule types represent the five stages through which input sentences pass starting from natural language sentences passing through syntactic trees and finally forming the semantic network. figure 2. illustrates the elaborate design of the analysis grammar as postulated by the UNL+3 program showing the five stages of analysis. ...
Similar publications
Problem statement: Grammatical Relation (GR) can be defined as a linguistic relation established by grammar, where linguistic relation is an association among the linguistic forms or constituents. Fundamentally the GR determines grammatical behaviors such as: placement of a word in a clause, verb agreement and the passivity behavior. The GR of Arab...
Nowadays, the understanding and generation of cognitive processes of natural language are becoming easier and better understood to
perform machine translation. In this paper, we develop a system of machine translation to translate from English to Arabic, which runs on PC compatibles with English/Arabic interface. The system task was to analyze the...
Citations
... These features include complicated semantics, grammars and morphologies due to the complex derivational and inflectional characteristics of the language. Hence, natural language processing systems designed for English are unable to handle the processing requirements of the Arabic language [4]. For instance, performing part-of-speech (POS) tagging on Arabic text is more complicated than on English text. ...
There are limited research contributions targeting sentiment analysis in feedback in Arabic gulf dialect, in particular, and the Arabic language in general. Furthermore, the inadequate and limited adoption of classification techniques and natural language processing is noticeable in the sentiment analysis projects addressing the Arabic language. Hence, this paper focuses on analyzing the sentiments in automobile and real estate domains through the application of the state-of-the-art word-embedding model "BERT" and a collection of deep learning models (GRU, LSTM, CNN, CNN-GRU and BiLSTM). The results of classification revealed that combining the BERT with deep learning models have shown efficiency in analyzing sentiments and yielded outstanding results.
... However, adequate natural language processing studies focusing on the Arabic language are arguably not proportional to the language proliferation [3]. The Arabic language has many variations in terms of formal and informal terminologies in both written and spoken language across the Arab countries. ...
The studies addressing the application of machine and deep learning models to analyze the sentiments of Arabic online reviews related to the real-estate and automobile fields are not mature. To fill this gap, this research has focused on classifying three types of sentiments in Arabic real-estate and automobile online reviews, which are negative, positive, and mixed sentiments. The research focused on analyzing the reviews written in both Gulf Cooperation Council (GCC) dialects and modern standard Arabic (MSA). The research also explained the natural language processing strategies that were adopted to prepare the text for classification. The research discussed the details of collecting and annotating the data, preprocessing procedures, and feature selection methods. Following this, the research highlighted the adopted strategies for balancing and splitting the datasets, and it showed the analysis of the classification results for both machine and deep learning models. Finally, the suggestions for future work were provided in this research.
... The other type of Arabic forms called Classical Arabic (CA), which is the language of the Holy Quran and Literary texts and poetic poems. This language talked by the Arabian people for more than fourteen centuries [3]. Public dialects are another type that varies depending on where you live [4]. ...
... Concerning Semantic analyzers, there is only two works devoted to semantically analyze Arabic sentences. The first approach presented by SamehAlansary (Alansary et al., 2013), which introduced the UNL framework, is able to analyze automatically natural languages into their abstract semantic meanings, with the aim of finding the common denominator between all languages. Moreover, the data is exportable in several different formats. ...
... Other uses of the NLP are those applied to linguistics to help translate or create tools to process certain languages. In this first article [94], the authors developed a framework to promote collaboration between linguists and non-linguists in the use of NLP applications for the Arabic language. On the other hand, in [84] they presented a simulation of the parser for Bahasa Indonesia, which is the language of Indonesia, due to the lack of research in this area for this language. ...
Humankind has the ability of learning new things automatically due to the capacities with which we were born. We simply need to have experiences, read, study... live. For these processes, we are capable of acquiring new abilities or modifying those we already have. Another ability we possess is the faculty of thinking, imagine, create our own ideas, and dream. Nevertheless, what occurs when we extrapolate this to machines? Machines can learn. We can teach them. In the last years, considerable advances have been done and we have seen cars that can recognise pedestrians or other cars, systems that distinguish animals, and even, how some artificial intelligences have been able to dream, paint, and compose music by themselves. Despite this, the doubt is the following: Can machines think? Or, in other words, could a machine which is talking to a person and is situated in another room make them believe they are talking with another human? This is a doubt that has been present since Alan Mathison Turing contemplated it and it has not been resolved yet. In this article, we will show the beginnings of what is known as Artificial Intelligence and some branches of it such as Machine Learning, Computer Vision, Fuzzy Logic, and Natural Language Processing. We will talk about each of them, their concepts, how they work, and the related work on the Internet of Things fields.
... Therefore, the UNL dictionary provides enough information to understand semantic structure of a sentence. Moreover, many research works use UNL for NLP tasks [35] [36]. ...
The explosion of information available on the Internet motivates researchers to semantically manipulate this information to enable Internet users to find what they actually need easily. One of the important pillars to manipulate data semantically is ontology. Arabic ontology is recently gains a lot of attention. This paper survey some available Arabic ontologies and compares between these ontologies to clarify the difference between the main categories of Arabic ontologies. Ontology creation approach and representation method is considered in this study.
... still limited to right-to-left Samsung S-Voice, for exam anguage has imposed many challenges in terms of the l ample, prefixes, suffixes, and pronouns in Arabic are aking a new word, which would be challenging to proc dentified and described several challenges and sugges nterested researchers and practitioners working on Ara g. Several other research studies have been conducted ges of the Arabic natural language processing and sugg [8] and [9]. ...
Electronic and mobile learning in recent years has been considered as an invaluable tool to support the learning process. Several tools and comprehensive platforms have been developed in the paradigms of e-learning and m-learning. One issue is the usability of these tools. It is essential to define metrics to measure efficiency, learnability, satisfaction and other usability properties. Another equally important issue is the presence of guidelines compiled based on accumulated scientific reasoning behind design decisions. In this paper, we discuss the issue of HCI-based guideline specific to designing e- and m-learning platforms and tools intended for Arabic users. We present our analysis on the availability of such guidelines, their deployment and to whether they adequately address the challenges characteristic to Arabic language.
Extraction of knowledge data from knowledge database using natural language query is a difficult task. Different types of natural language processing (NLP) techniques have been developed to handle this knowledge data extraction task. This paper proposes an automated query-response model termed Extended Automated Knowledge Provider System (EAKPS) that can manage various types of natural language queries from user. The EAKPS uses combination based technique and it can handle assertive, interrogative, imperative, compound and complex type query sentences. The algorithm of EAKPS generates structure query language (SQL) for each natural language query to extract knowledge data from the knowledge database resident within the EAKPS. Extraction of noun or noun phrases is another issue in natural language query processing. Most of the times, determiner, preposition and conjunction are prefixed to a noun or noun phrase and it is difficult to identify the noun/noun phrase with prefix during query processing. The proposed system is able to identify these prefixes and extract exact noun or noun phrases from natural language queries without any manual intervention.
Diacritization of written text has a significant impact on Arabic NLP applications. We present an approach to Arabic automatic diacritization that integrates morphological analysis with shallow syntactic analysis. The developed system (Alserag) is a rule based system. The system depends on three modules in order to provide fully diacritized Arabic words namely, morphological analysis module, syntactic analysis module and morph-phonological processing module. To evaluate the performance of the system, we used the benchmark LDC Arabic Treebank datasets used by the state-of-the-art systems (Metwally et al. 2016; Zitouni 2006) and (Shahrour et al. 2015). The proposed system achieved a morphological WER of 5.6%, and a syntactic WER of 10.1%.
