International Journal of Computer Processing of Languages

In this paper, we build statistical language models for the Persian language using a Persian corpus called Peykare. Then, we incorporate the constructed language models in a Persian continuous speech recognition (CSR) system. First, we unify the different orthographies of words to make the texts of the corpus consistent. In addition, we decrease the number of POS tags used in the corpus by manual clustering. Then, the word-based and the class-based n-gram language models are built using the unified and reduced-tag-set corpus. For building the class-based language models, several methods are used including a new method called LGM-based word clustering. We present the procedure of incorporating language models in a Persian CSR system. Using these language models absolute reductions of up to 13.2% in word error rate were achieved.

An appraisal expression is described as a collocation of the polarity word and its modified target, which can be considered as an atomic unit expressing an evaluative stance towards a target. Recognizing appraisal expressions is essential for sentence sentiment classification. However, the relevant research is far from enough. This paper proposes a novel method that uses syntactic paths to recognize appraisal expressions. Compared with the previous work, the proposed syntactic path based method has two advantages: 1) it automatically explores syntactic knowledge, and 2) it covers more syntactic relationships between polarity words and targets. Based on these, this paper applies appraisal expressions to sentence sentiment classification. Some novel features based on appraisal expressions, including semantic features, syntactic features, lexical features and polarity features, are designed to classify sentiment sentences as positive or negative. Experimental results on the camera and MP3 player domains show that the proposed appraisal expression based method outperforms other sentence sentiment classification methods. Moreover, we present a composite classifier to integrate our appraisal expression based feature set and the common-used feature set. Experimental results show that our composite classifier can get a better performance than each of them.

We present a hybrid approach to the problem of Arabic text summarization. Our approach focuses on segment extraction and ranking using heuristic methods that assign weighted scores to segments of text. Also, we use a text categorization system and the Arabic WordNet to identify the thematic structure of the input text in order to select the most relevant sentences obtained from the statistical analysis process. We use a tokenizer, a stemmer and other statistical tools borrowed from traditional information retrieval to identify relevant segments in the text. The source document is segmented into its major units (title, paragraphs and lines) and then, text-lines are interpreted to extract relevant segments for inclusion in the summary. The summarization system was tested by 1200 human evaluators, who were each given a copy of a newspaper article and a system-generated summary and asked to classify them as "rejected," "not-related," "satisfactory," "good," or "accepted." 76.92% of the summaries were judged to be "good" or "accepted" and 92.34% were judged to be "satisfactory," or "good," or "accepted." These results confirm the viability of using this hybrid approach to tackle the problem of Arabic text summarization.

In this study, we present a robust bottom-up Arabic parser that investigates the correctness of Arabic sentences by passing them through a set of predetermined states relying on their individual words. The major benefit of our approach is the reduced number of backup states tested when determining the grammatical structure of a given sentence. The proposed approach is optimized to tokenize the input sentences correctly since accurate tokenization is the essential step of the parser; this process also reduces the parsing time. Our proposed parser is extendable; hence, it allows new words to be added to the lexicon, i.e. the lexicon is built dynamically. Experimental results have demonstrated the effectiveness of our approach in checking correctly numerable sentences with different lengths. The accuracy was 85.88% when tested on a sample of 170 Arabic sentences taken from an existing Arabic text taught in k-12 grade levels.

Text Categorization (TC) has become one of the major techniques for organizing and managing online information. Several studies proposed the so-called associative classification for databases and few of these studies are proposed to classify text documents into predefined categories based on their contents. In this paper a new approach is proposed for Arabic text categorization. The approach facilitates the discovery of association rules for building a classification model for Arabic text categorization. An apriori based algorithm is employed for association rule mining. To validate the proposed approach, several experiments were applied on a collection of Arabic documents. Three classification methods using association rules were compared in terms of their classification accuracy; the methods are: ordered decision list, weighted rules, and majority voting. The results showed that the majority voting method is the best in most of experiments achieving an accuracy of up to 87%. On the other hand, the weighted rule method was the worst in all experiments. Generally, the results of the experiments showed that association rule mining is a suitable method for building good classification models to categorize Arabic text.