Disambiguating Arabic Words According to Their Historical Appearance in the Document Based on Recurrent Neural Networks

Abstract

How can we determine the semantic meaning of a word in relation to its context of appearance? We eventually have to grabble with this difficult question, as one of the paramount problems of Natural Language Processing (NLP). In other words, this issue is commonly defined as Word Sense Disambiguation (WSD). The latter is one of the crucial difficulties within the NLP field. In this respect, word vectors extracted from a neural network model have been successfully applied for resolving the WSD problem. Accordingly, this article presents an unprecedented method to disambiguate Arabic words according to both their contextual appearance in a source text and the era in which they emerged. In fact, in the few previous decades, many researchers have been grabbling with Arabic Word Sense Disambiguation. It should be noted that the Arabic language can be divided into three major historical periods: old Arabic, middle-age Arabic, and contemporary Arabic. Actually, contemporary Arabic has proved to be the greatest concern of many researchers. The main gist of our work is to disambiguate Arabic words according to the historical period in which they appeared. To perform such a task, we suggest a method that deploys contextualized word embeddings to better gather valid syntactic and semantic information of the same word by taking into account its contextual uses. The preponderant thing is to convert both the senses and the contextual uses of an ambiguous item to vectors, then determine which of the possible conceptual meanings of the target word is closer to the given context.

Arabic Gloss WSD Using BERT

“…The authors in [24] used Rough Set Theory and semantic short text similarity to measure the semantic relatedness between the target word's context and multiple possible concepts (gloss). Recently, The authors in [25] used FLAIR [26], a character-level language model, to generate sentence representation vectors for both context and gloss sentences. The sentence's vector was calculated by taking the mean of its word vectors, causing a loss of information, especially when the sequence is long.…”

“…Table 9 compares our proposed models against other embedding based models that depend on representing gloss and the context sentences in the vector space such as in our model. We compare our proposed models with two models, Laatar [25] and Laatar [23] which are the most recent Arabic WSD works. The test data of the two models are not available; thus, in order to make a fair comparison, we redeveloped their models and tested them on our benchmark.…”

“…The test data of the two models are not available; thus, in order to make a fair comparison, we redeveloped their models and tested them on our benchmark. Laatar [25] used FLAIR [26] to generate word embedding. FLAIR is a pretrained character level language model.…”

“…FLAIR is a pretrained character level language model. Laatar [25] represents each sentence by the mean of its words vectors. The authors in [23] used Word2Vec [15] language model to represent the words of the sentence in the vector space and then they represented the sentence by adding its words vector representation.…”

Principal Component Analysis and Prediction of Students’ Physical Health Standard Test Results Based on Recurrent Convolution Neural Network

“…The times require them not only to have a comprehensive and solid scientific culture and outstanding talents but also to have a strong physique. Therefore, only the health of students is an important prerequisite for improving academic performance and cultivating crosscentury talents [20]. Based on this, the health problem of contemporary college students is not only a personal problem but also a social problem.…”