Contribution to Semantic Analysis of Arabic Language

Polibits, 2012

In this paper we test some supervised algorithms that most of the existing related works of word sense disambiguation have cited. Due to the lack of linguistic data for the Arabic language, we work on non-annotated corpus and with the help of four annotators; we were able to annotate the different samples containing the ambiguous words. Since that, we test the Naïve Bayes algorithm, the decision lists and the exemplar based algorithm. During the experimental study, we test the influence of the window size on the disambiguation quality, the derivation and the technique of smoothing for the (2n+1)-grams. For these tests the exemplar based algorithm achieves the best rate of precision.

2013 International Conference on Electrical Engineering and Software Applications, 2013

In this paper we propose an unsupervised method for Arabic word sense disambiguation. Using the corpus and the glosses of the ambiguous word, we define a method to generate automatically the context of use for each sense. Since that, we define a similarity measure based on collocation measures to find the most nearest context of use to the sentence containing the ambiguous word. The similarity measure may give more than one sense, for that we define a novel supervised approach called vote procedure. Our work was compared with other related works. We obtained a better rate of disambiguation in the average of 79%.

Speech and Language Technology, 2009

We are presenting a word sense disambiguation method applied in automatic translation of a query from Arabic into English. The developed machine learning approach is based on statistical models, that can learn from parallel corpora by analysing the relations between the items included in this corpora in order to use them in the word sense disambiguation task. The relations between items in this corpora are obtained by using and developing a purely statistical method from corpora in order to avoid the use of structured linguistic resources like ontology which are not yet available for Arabic in an appropriate quality. The results of this analysis should provide us with some useful semantic information that can help to find the best translation equivalents of the polysemous items.

Int. Arab J. Inf. Technol., 2016

In this paper, we present two contributions for Arabic Word Sense Disambiguation. In the first one, we propose to use both two external resources Arabic WordNet (AWN) and WN based on term to term Machine Translation System (MTS). The second contribution consists of choosing the nearest concept for the ambiguous terms, based on more relationships with different concepts in the same local context. To evaluate the accuracy of our proposed method, several experiments have been conducted using Feature Selection methods; Chi-Square and CHIR, two machine learning techniques; the Naïve Bayesian (NB) and Support Vector Machine (SVM).The obtained results illustrate that using the proposed method increases greatly the performance of our Arabic Text Categorization System.

The limited coverage of available Arabic language lexicons causes a serious challenge in Arabic cross language information retrieval. Translation in cross language information retrieval consists of assigning one of the semantic representation terms in the target language to the intended query. Despite the problem of the completeness of the dictionary, we also face the problem of which one of the translations proposed by the dictionary for each query term should be included in the query translations. In this paper, we describe the implementation and evaluation of an Arabic/English word translation disambiguation approach that is based on exploiting a large bilingual corpus and statistical co-occurrence to find the correct sense for the query translations terms. The correct word translations of the given query term are determined based on their cohesion with words in the training corpus and a special similarity score measure. The specific properties of the Arabic language that frequently hinder the correct match are taken into account.

International Journal of Advanced Computer Science and Applications, 2012

In the information systems, the query's expansion brings more benefices in the relevant documents extraction. However, the current expansion types are focused on the retrieve of the maximum of documents (reduce the silence). In Arabic, the queries are derived in many morphosemantical variants. Hence the diversity of the semantic interpretations that often creates a problem of ambiguity. Our objective is to prepare the Arabic request before its introduction to the document retrieval system. This type of preparation is based on pretreatment which makes morphological changes to the query by separating affixes of the words. Then, present all of morphosemantical derivatives as a first step to the lexical audit agent, and check the consistency between the words by the context parser. Finally we present a new method of semantic similarity based on the equivalence probability calculation between two words.

Word sense disambiguation is a core problem in many tasks related to language processing and was recognized at the beginning of the scientific interest in machine translation and artificial intelligence. In this paper, we introduce the possibilities of using the Support Vector Machine (SVM) classifier to solve the Word Sense Disambiguation problem in a supervised manner after using the Levenshtein Distance algorithm to measure the matching distance between words through the usage of the lexical samples of five Arabic words. The performance of the proposed technique is compared to supervised and unsupervised machine learning algorithms, namely the Naïve Bayes Classifier (NBC) and Latent Semantic Analysis (LSA) with K-means clustering, representing the baseline and state-of-the-art algorithms for WSD.

Word sense ambiguity is widely spread in all natural languages; a word may carry several distinct meanings. Human can figure out the suitable meaning according to the context in which the word occurs. The Arabic language is highly polysemous; in many situations we find it extremely necessary to disambiguate the word senses. This paper studies and compares the performance of a search engine before and after expanding the query through Interactive Word Sense Disambiguation (WSD). We found that expanding polysemous query terms by adding more specific synonyms will narrow the search into the specific targeted request and thus causes both precision and recall to increase; on the other hand, expanding the query with a more general (polysemous) synonym will broaden the search which would cause the precision to decrease.

IRAQI JOURNAL OF SCIENCE, 2017

Query expansion (QE) is a successful idea to overcome the weaknesses in the information retrieval performance. The QE requires finding out appropriate word synonyms of the query words in a process that can be made automatically without any user intervention. The candidate synonyms should be associated with an accurate meaning (sense) of the original word. Arabic language is rich in multiple meanings and this requires using the so-called word sense disambiguation (WSD). WSD in general is a task to discover the correct sense of a word within context. To disambiguate the word sense, three different traditional semantic measures are tested in this work; they are called lch, wup, and path respectively. The proposed system uses these measures along with an automatic synonym selection method employed to expand the query. The proposed system outperforms the traditional baseline system that has no query expansion technique in a rate from 10% to 18 % and reduces the latency in an approximate rate from 0.232 to 0.283 second for each query.

The problem underlying this research is to solve word sense disambiguation problem for Urdu language text. Although the problem is well-studied for English language text, the work on Urdu is still in infancy. Since Urdu is a morphologically a rich language and hence very sparse, it may not be guaranteed that the methods that performance better for English language may also be effective for Urdu. The goal of this research is to propose a method for word sense disambiguation of ambiguous Urdu words and develop a prototype system. We have proposed a two-stage method where the first stage is detection phase and second stage is identification phase. The detection task is performed by maintaining a lexicon of ambiguous words. The identification problem is posed as a classification problem where a classifier is trained for each ambiguous word by developing a word sense disambiguation specific test collection. Two well-studied text classification algorithms have been analyzed for classification: support vector machine and Naïve Bayes. The results have shown that support vector machine has an advantage due to it intrinsic ability to handle sparse data and less sensitivity to high dimensionality of dataset. I. INTROUDCTION Information extraction (IE) is the task of automatically extracting structured information from unstructured and/or semi-structured machine-readable documents.. This extraction is basically applied on structured and semi-structured textual data that is readable to machine. However, the techniques of automatic annotation and content extraction from multimedia are also considered in IE. In IE, main goal is to automatically extract entities from data on the web, finding the relationships among entities and describing attributes of entities. The extracted knowledge enables much richer forms of queries on the abundant unstructured sources than possible with keyword searches alone. Another objective of IE is to represent the unstructured text in a form useful to derive inferences that are based on the logical content found in the input data. Assigning a correct sense automatically to a word that has more than one meaning is referred as word sense disambiguation (WSD). Many words have more than one meaning having correct sense in a particular context for which WSD technique is introduced. Word sense disambiguation is a process to resolve the ambiguity and rectify the use of word in a specific frame of reference [1]. Human are good to identify the correct sense of word with the help of context easily. WSD is a domain that deals with modeling this ability of humans into computers. Frequently it is noticed that some words may have multiple meanings according to their use as parts Of speech (POS). In the following example same word (bear) gives us a sense of verb and noun in two different sentences.