Transliterate English words into Arabic by render them in the orthography of the Arabic language and vise versa.
Out of vocabulary (OOV) words are a common source of errors in cross language information retrieval. Bilingual dictionaries are often limited in their coverage of named entities, numbers, technical terms and acronyms. There is a need to generate translations for these "on-the-fly" or at query time. A significant proportion of OOV words are named entities and technical terms. Typical analyses finds around 50% of OOV words to be named entities. Yet these can be the most important words in the queries. Cross language retrieval performance (average precision) reduced more than 50% when named entities in the queries were not translated. When the query language and the document language share the same alphabet it may be sufficient to use the OOV word as its own translation. However, when the two languages have different alphabets, the query term must somehow be rendered in the orthography of the other language. The process of converting a word from one orthography into another is called transliteration.
Foreign words often occur in Arabic text as transliteration. This is the case for many categories of foreign words, not just proper names but also technical terms such as caviar, telephone and internet.
|
English (auto generated) |
Arabic (sample input) |
| Khalid Ash-Sham'ah | خالِد الشَمعَة |
| Jubran Khalyl Jubran | جُبران خَليل جُبران |
| Kazim As-Sahir | كاظِم الساهِر |
| Majidat Ar-Roumi | ماجِدَة الرُومِي |
| Nizar Qab'bani | نِزار قَبَّانِي |
| Souq Al-Hameidei'iah? | سُوق الحَمِيدِيَّة؟ |
| Magharat Ja'eita | مَغارَة جَعِيتَا |
| Ghoutat Dimashq | غُوطَة دِمَشق |
| Halab Ash-Shahba'a | حَلَب الشَهبَاء |
| Jazyrat Aarwad | جَزيرَة أَرواد |
| Bilad Ar-Rafidan | بِلاد الرافِدَين |
| Ahramat Al-Jeizah | أهرامات الجِيزَة |
| Dira | دِرْع |
| Eid | عِيد |
| Oud | عُود |
| Rid'a | رِدْء |
| Eida'a | إِيدَاء |
| Hibat Al-Lh | هِبَة الله |
| Qadin | قاضٍ |
<?php
$Arabic = new \ArPHP\I18N\Arabic();
$ar_terms = array('خالِد الشَمعَة', 'جُبران خَليل جُبران', 'كاظِم الساهِر',
'ماجِدَة الرُومِي', 'نِزار قَبَّانِي', 'سُوق الحَمِيدِيَّة؟', 'مَغارَة جَعِيتَا',
'غُوطَة دِمَشق', 'حَلَب الشَهبَاء', 'جَزيرَة أَرواد', 'بِلاد الرافِدَين',
'أهرامات الجِيزَة', 'دِرْع', 'عِيد', 'عُود', 'رِدْء', 'إِيدَاء', 'هِبَة الله', 'قاضٍ');
echo <<< END
<center>
<table border="0" cellspacing="2" cellpadding="5" width="500">
<tr>
<td bgcolor="#27509D" align="center" width="150">
<b>
<font color="#ffffff" face="Tahoma">
English<br />(auto generated)
</font>
</b>
</td>
<td bgcolor="#27509D" align="center" width="150">
<b>
<font color="#ffffff">
Arabic<br />(sample input)
</font>
</b>
</td>
</tr>
END;
foreach ($ar_terms as $term) {
echo '<tr><td bgcolor="#f5f5f5" align="left"><font face="Tahoma">';
echo $Arabic->ar2en($term);
echo '</font></td>';
echo '<td bgcolor="#f5f5f5" align="right">'.$term.'</td></tr>';
}
echo '</table></center>';