An Empirical Study of Arabic Formulaic Sequence Extraction Methods

An Empirical Study of Arabic Formulaic Sequence Extraction Methods Ayman Alghamdi, Eric Atwell, Claire Brierley School of Computing, University of Leeds Woodhouse Lane Leeds, LS2 9JT UK. scaaa@leeds.ac.uk, e.s.atwell@leeds.ac.uk, c.brierley@leeds.ac.uk Abstract This paper aims to implement what is referred to as the collocation of the Arabic keywords approach for extracting formulaic sequences (FSs) in the form of high frequency but semantically regular formulas that are not restricted to any syntactic construction or semantic domain. The study applies several distributional semantic models in order to automatically extract relevant FSs related to Arabic keywords. The data sets used in this experiment are rendered from a new developed corpus-based Arabic wordlist consisting of 5,189 lexical items which represent a variety of modern standard Arabic (MSA) genres and regions, the new wordlist being based on an overlapping frequency based on a comprehensive comparison of four large Arabic corpora with a total size of over 8 billion running words. Empirical n-best precision evaluation methods are used to determine the best association measures (AMs) for extracting high frequency and meaningful FSs. The gold standard reference FSs list was developed in previous studies and manually evaluated against well-established quantitative and qualitative criteria. The results demonstrate that the MI.log_f AM achieved the highest results in extracting significant FSs from the large MSA corpus, while the T-score association measure achieved the worst results. Keywords: Arabic, Formulaic Sequence, Association Measures 1. Introduction In recent decades, the phenomenon of formulaic language has witnessed a proliferation from various perspectives within the research community (e.g. linguistic, psycholinguistic natural language processing 'NLP' and language pedagogy 'LP'). Many studies that have been conducted in these areas show the key role that formulaic language plays in our use of everyday languages. Even though most modern languages have benefitted from a large amount of research in this area, the multidisciplinary and heterogeneous nature of this complex linguistic phenomenon requires more researchers' attention using various methodologies borrowed from a range of different related scientific perspectives. This research will ultimately contribute to the improvement of our understanding of the linguistic behaviour of FSs and its implications for language applications such as lexicography, information retrieval, machine translation, and word sense disambiguation. Research into Arabic FSs is still underdeveloped, particularly research that makes use of MSA corpus-based analysis techniques which enable researchers to build their linguistic assumptions on real used language. In the field of Arabic LP and NLP, there is an urgent need for developing new corpus-based FSs language resources which can be used in various related applications. Therefore, the current study aims to remedy this deficiency by introducing a new corpus-based list of FSs based on an empirical evaluation of Statistical Association Measures (AMs). However, it is worth mentioning here that this study is part of a larger ongoing research project that aims to build an intensive Arabic FSs lexicon for use in LP and NLP. Extracting the most common and meaningful FSs associated with a frequency based Arabic wordlist - our primary concern in this study - can …

Content truncated to 500 words