English-Arabic Phonetic Dataset construction

Abstract

In the field of natural language processing, the effectiveness of a semantic similarity task is significantly influenced by the presence of an extensive corpus. While numerous monolingual corpora exist, predominantly in English, the availability of multilingual resources remains quite restricted. In this study, we present a semi- automated framework designed for generating a multilingual phonetic English- Arabic corpus, specifically tailored for application in multilingual phonetically and semantic similarity tasks. The proposed model consists of four phases: data gathering, preprocessing and translation, extraction IPA representation, and manual correction. Four datasets were used one of them was constructed from many sources. A manual correction was used at all the levels of the system to produce a golden standard dataset. The final dataset was in the form (English Word, English Phonetic, equivalent Arabic Word, and Arabic Phonetic). Also, a deep learning approach was used for extracting International Phonetic Alphabet (IPA) phonetic representation where the results for 13400 samples show that the Phonetic Error Rate (PER) and accuracy were 11.96% and 88.04 % respectively which are good results for producing IPA representation for unknown English and Arabic names.