No abstract

Corpus Resources for Descriptive and Applied Studies. Current Challenges and Future Directions: Selected Papers from the 5th International Conference on Corpus Linguistics (CILC2013)International audienceParallel corpora are not available for all domains and languages, but statistical methods in multilingual research domains require huge parallel/comparable corpora. Comparable corpora can be used when the parallel is not sufficient or not available for specific domains and languages. In this paper, we propose a method to extract all comparable articles from Wikipedia for multiple languages based on interlanguge links. We also extract comparable articles from Euro News website. We also present two comparability measures (CM) to compute the degree of comparability of multilingual articles. We extracted about 40K and 34K comparable articles from Wikipedia and Euro News respectively in three languages including Arabic, French, and English. Experimental results of comparability measures show that our measure can capture the comparability of multilingual corpora and allow to retrieve articles from different language concerning the same topic

Abstract. We aim in this research to find and compare cross-lingual articles concerning a specific topic. So, we need a measure for that. This measure can be based on bilingual dictionaries or based on numerical methods such as Latent Semantic Indexing (LSI). In this paper, we use the LSI in two ways to retrieve Arabic-English comparable articles. The first one is monolingual: the English article is translated into Arabic and then mapped into the Arabic LSI space; the second one is crosslingual: Arabic and English documents are mapped into Arabic-English LSI space. Then, we compare LSI approaches to the dictionary-based approach on several English-Arabic parallel and comparable corpora. Results indicate that the performance of cross-lingual LSI approach is competitive to monolingual approach, or even better for some corpora. Moreover, both LSI approaches outperform the dictionary approach.

No abstract

Abstract. We present, in this paper an Arabic multi-dialect study including dialects from both the Maghreb and the Middle-east that we compare to the Modern Standard Arabic (MSA). Three dialects from Maghreb are concerned by this study: two from Algeria and one from Tunisia and two dialects from Middle-east (Syria and Palestine). The resources which have been built from scratch have lead to a collection of a multi-dialect parallel resource. Furthermore, this collection has been aligned by hand with a MSA corpus. We conducted several analytical studies in order to understand the relationship between these vernacular languages. For this, we studied the closeness between all the pairs of dialects and MSA in terms of Hellinger distance. We also performed an experiment of dialect identification. This experiment showed that neighbouring dialects as expected tend to be confused, making difficult their identification. Because the Arabic dialects are different from one region to another which make the communication between people difficult, we conducted cross-lingual machine translation between all the pairs of dialects and also with MSA. Several interesting conclusions have been carried out from this experiment.