Maytham Alabbas

Natural language inference for arabic using extended tree edit distance with subtrees

Many natural language processing (NLP) applications require the computation of similarities between pairs of syntactic or semantic trees. Many researchers have used tree edit distance for this task, but this technique suffers from the drawback that it deals with single node operations only. We have extended the standard tree edit distance algorithm to deal with subtree transformation operations as well as single nodes. The extended algorithm with subtree operations, TED+ST, is more effective and flexible than the standard algorithm, especially for applications that pay attention to relations among nodes (e.g. in linguistic trees, deleting a modifier subtree should be cheaper than the sum of deleting its components individually). We describe the use of TED+ST for checking entailment between two Arabic text snippets. The preliminary results of using TED+ST were encouraging when compared with two string-based approaches and with the standard algorithm.

Evaluation of dependency parsers for long Arabic sentences

The aim of the work reported here is to investigate the effectiveness of dependency parsing for the analysis of Arabic. Arabic has a number of characteristics, described below, which make parsing it particularly challenging. The results of our investigations suggest that dependency parsing can produce reasonably accurate results. We show in particular that combining the output of two different parsers can produce more accurate results than either parser produces by itself.

Improved POS-Tagging for Arabic by Combining Diverse Taggers

A number of POS-taggers for Arabic have been presented in the literature. These taggers are not in general 100% accurate, and any errors in tagging are likely to lead to errors in the next step of natural language processing. The current work shows an investigation of how the best taggers available today can be improved by combining them. Experimental results show that a very simple approach to combining taggers can lead to significant improvements over the best individual tagger.

BASRAH: Arabic Verses Meters Identification System

In this paper, we present BASRAH, a system that automatically identifies the meter of Arabic verse, which is an operation that requires a certain level of human expertise. BASRAH uses the numerical prosody method, which depends on verse coding that is derived from the general concept of al-Khalils feet through using the two primary units (cord=2 and peg=3). BASRAH has proved to be an efficient tool to help inexperienced users to determine the meters of Arabic verses when we tested it on thousands of old and modern Arabic verses.

Optimize BpNN Using New Breeder Genetic Algorithm

In this paper, the ability of genetic algorithms in designing artificial neural network (ANN) is investigated. The multi-layer network (MLN) is taken into account as the ANN structure to be optimized. The idea presented here is to use the genetic algorithms to yield contemporaneously the optimization of: (1) the design of NN architecture in terms of number of hidden layers and of number of neurons in each layer; and (2) the choice of the best parameters (learning rate, momentum term, activation functions, and order of training patterns) for the effective solution of the actual problem to be faced. The back-propagation (BP) algorithm, which is one of the best-known training methods for ANNs, is used. To verify the efficiency of the current scheme, a new version of the breeder genetic algorithm (NBGA) is proposed and used for the automatic synthesis of NN. Finally, several problems of the experiment were taken and the results show that the back-propagation neural network (BpNN) classifier improved the current scheme has higher accuracy of classification and greater gradient of convergence than other classifiers, which have been proposed in the literature.

Combining strategies for tagging and parsing Arabic

We describe a simple method for combining taggers which produces substantially better performance than any of the contributing tools. The method is very simple, but it leads to considerable improvements in performance: given three taggers for Arabic whose individual accuracies range from 0.956 to 0.967, the combined tagger scores 0.995‐a sevenfold reduction in the error rate when compared to the best of the contributing tools. Given the effectiveness of this approach to combining taggers, we have investigated its applicability to parsing. For parsing, it seems better to take pairs of similar parsers and back off to a third if they disagree.

Improved Parsing for Arabic by Combining Diverse Dependency Parsers

Recently there has been a considerable interest in dependency parsing for many reasons. First, it works accurately for a wide range of typologically different languages. Second, it can be useful for semantics, since it can be easier to attach compositional rules directly to lexical items than to assign them to large numbers of phrase structure rules. Third, robust machine-learning based parsers are available. In this paper, we investigate two techniques for combining multiple data-driven dependency parsers for parsing Arabic, where we are faced with an exceptional level of lexical and structural ambiguity. Experimental results show that combined parsers can produce more accurate results, even for imperfectly tagged text, than each parser produces by itself for texts with the gold-standard tags.