Catalogue Search | MBRL
Are you sure you want to remove the book from the shelf?
{{itemTitle}}
6
result(s) for
"Arabic language Forecasting."
Sort by:
When You Think About It, Your Past Is in Front of You: How Culture Shapes Spatial Conceptions of Time
In Arabic, as in many languages, the future is \"ahead\" and the past is \"behind.\" Yet in the research reported here, we showed that Arabic speakers tend to conceptualize the future as behind and the past as ahead of them, despite using spoken metaphors that suggest the opposite. We propose a new account of how space-time mappings become activated in individuals' minds and entrenched in their cultures, the temporal-focus hypothesis: People should conceptualize either the future or the past as in front of them to the extent that their culture (or subculture) is future oriented or past oriented. Results support the temporal-focus hypothesis, demonstrating that the space-time mappings in people's minds are conditioned by their cultural attitudes toward time, that they depend on attentional focus, and that they can vary independently of the space-time mappings enshrined in language.
Journal Article
Predicting Arabic word reading: A cross-classified generalized random-effects analysis showing the critical role of morphology
The distinctive features of the Arabic language and orthography offer opportunities to investigate multiple word characteristics at the item level. The aim of this paper was to model differences in word reading at the item level among 3rd grade native Arabic-speaking children (
n
= 303) using cross-classified generalized random-effects (CCGRE) analysis. The participants read 80 vowelized words that varied in multiple elements that may contribute to their decodability: number of letters, number of syllables, number of morphemes, ligaturing (connectivity), semantics (concrete vs. abstract), orthographic frequency, root type frequency, and part of speech. Morphological awareness (MA) was included as a person-level predictor. Results of individual models showed that MA, number of letters, number of syllables, number of morphemes, number of ligatures, orthographic frequency, and part of speech were significantly related to the probability of a correct response. However, when all predictors were entered simultaneously, only MA and number of morphemes remained significant. These results underscore the important role of morphology in the lexical structure of Arabic words and in Arabic word reading. Discussion focuses on the role of morphology in Arabic reading and the implications for intervention to improve word recognition in children learning to read Arabic.
Journal Article
Revealing the Next Word and Character in Arabic: An Effective Blend of Long Short-Term Memory Networks and ARABERT
Arabic raw audio datasets were initially gathered to produce a corresponding signal spectrum, which was further used to extract the Mel-Frequency Cepstral Coefficients (MFCCs). The pronunciation dictionary, language model, and acoustic model were further derived from the MFCCs’ features. These output data were processed into Baidu’s Deep Speech model (ASR system) to attain the text corpus. Baidu’s Deep Speech model was implemented to precisely identify the global optimal value rapidly while preserving a low word and character discrepancy rate by attaining an excellent performance in isolated and end-to-end speech recognition. The desired outcome in this work is to forecast the next word and character in a sequential and systematic order that applies under natural language processing (NLP). This work combines the trained Arabic language model ARABERT with the potential of Long Short-Term Memory (LSTM) networks to predict the next word and character in an Arabic text. We used the pre-trained ARABERT embedding to improve the model’s capacity and, to capture semantic relationships within the language, we educated LSTM + CNN and Markov models on Arabic text data to assess the efficacy of this model. Python libraries such as TensorFlow, Pickle, Keras, and NumPy were used to effectively design our development model. We extensively assessed the model’s performance using new Arabic text, focusing on evaluation metrics like accuracy, word error rate, character error rate, BLEU score, and perplexity. The results show how well the combined LSTM + ARABERT and Markov models have outperformed the baseline models in envisaging the next word or character in the Arabic text. The accuracy rates of 64.9% for LSTM, 74.6% for ARABERT + LSTM, and 78% for Markov chain models were achieved in predicting the next word, and the accuracy rates of 72% for LSTM, 72.22% for LSTM + CNN, and 73% for ARABERET + LSTM models were achieved for the next-character prediction. This work unveils a novelty in Arabic natural language processing tasks, estimating a potential future expansion in deriving a precise next-word and next-character forecasting, which can be an efficient utility for text generation and machine translation applications.
Journal Article
ACS: an innovative Alzheimer’s care system
Alzheimer’s disease is a progressive neurological disorder that is very common among older adults. In truth, taking care of Alzheimer’s patients can be a very tedious job that requires a lot of time and effort. On the other hand, smartphone applications (apps) have become an essential part of all of our daily life fields. Almost every human activity can be related to an app from checking the weather forecasts to attending a business meeting online. As a natural result of this, many useful apps were developed to serve and help Alzheimer’s patients and families around the world. Sadly, the apps launched in the Arabic area were very poor in their content and limited in their features. In this work, we present Alzheimer’s care system (ACS) which is a smartphone Android app that aims to serve Alzheimer’s early stages patients, their caregivers, and their doctors. ACS has an Arabic interface along with the English one to serve the patients in the Arabic talking countries who may struggle using similar apps in other languages. The app provides three account types and includes many useful features like contacting the caregivers and doctors through messages, keeping track of daily life tasks, reminding the patient of medication doses and times, and many more. Moreover, ACS has a Chatbot that provides general knowledge regarding the disease. Our app has been practically tested for one month by a group of users who were asked to fill out a 12 questions survey at the end of the test period. The survey results were very positive and encouraging in general. As future work, we plan to add other languages, develop an iOS version, and add new features to the app.
Journal Article
درجة ممارسة أعضاء هيئة التدريس في قسم اللغة العربية في جامعة الحدود الشمالية لأسلوب التدريس التبادلي
هدفت هذه الدراسة إلى تعرف درجة ممارسة أعضاء هيئة التدريس ومن في حكمهم في قسم اللغة العربية في جامعة الحدود الشمالية لأسلوب التعليم التبادلي. وقد استخدمت الباحثتان المنهج الوصفي لتحقيق أهداف الدراسة، فقامتا ببناء استبانة مكونة من أربعة مجالات: التنبؤ والتساؤل والتوضيح والتلخيص، واندرج تحتها ستون فقرة، بعد اتفاق المحكمون حولها. وتكونت عينة الدراسة من (36) عضو من أعضاء هيئة التدريس ومن في حكمهم في قسم اللغة العربية في جامعة الحدود الشمالية، (15) من الذكور، و(21) من الإناث، العاملين في الفصل الدراسي الثاني من العام 1433/1434 م. وقد أظهرت نتائج الدراسة أن درجة ممارستهم لاستراتيجيات التعليم التبادلي كانت بدرجة ممارسة مرتفعة للاستراتيجيات جميعها، وأن لا يوجد أثر ذو دلالة إحصائية لمتغير الجنس على المستوى الكلي، ولا أثر ذو دلالة إحصائية لمتغير الخبرة. وأوصت الباحثتان بتوسيع استخدام أسلوب التعليم التبادلي في تدريس مهارات فهم المقروء، وتوجيه الباحثين لتجريب فاعلية المزيد من الاستراتيجيات والأساليب والنماذج التعليمية التي تستهدف تنمية فهم المقروء لدى الطلبة بمستوياتهم مختلفة.
Journal Article