You are here

Birzeit University symposium details efforts to create Arabic search engine

By JT - Feb 24,2019 - Last updated at Feb 24,2019

Birzeit University’s Mustafa Jarrar (right) speaks about a collaborative project to enrich Arabic content on the Internet through a dictionary search engine, the Arabic ontology engine and the Curras online corpus for the Palestinian dialect during a symposium organised by the Arab Renaissance for Democracy and Development (Photo courtesy of the ARDD)

AMMAN — Birzeit University’s Mustafa Jarrar recently reviewed eight years of work by his team to enrich Arabic content on the Internet through a dictionary search engine, the Arabic ontology engine and the Curras online corpus for the Palestinian dialect.

The presentation was made during a symposium, titled: “The Arabic ontology and computerising dictionaries”, which was organised by the Arab Renaissance for Democracy and Development (ARDD), in conjunction with the International Mother Language Day celebrated annually by UNESCO on February 21.

The dictionary search engine is the first of its kind, not only for the Arabic language but for all languages, and includes 150 digitised Arabic dictionaries, according a statement by organisers.

The engine provides accurate translation for foreign terms in a way that avoids several mistakes common to search engines like Google Translate, which uses statistical translation for the meanings of terms and words rather than a dictionary translation, the ARDD statement said.

Digitising the Arabic dictionaries required reprinting their contents manually to create an electronic copy with a “text format” to programme them and reinsert them into the search engine’s database. The project included more than 300 students from the university.

The university depended entirely on the team to finish the project, without receiving any outside financial support, Jarrar, associate professor of computer science, was quoted in the ARDD statement as saying.

“The Arabic ontology engine aims at controlling the ‘chaos’ in the Arabic language’s definitions and concepts, where two sides can use the same term with different meanings, which can lead to misunderstandings, confusion and disputes.”

The Curras engine works to improve the way search engines and computers comprehend the written and audio contents of informal dialects on the Internet, in addition to documenting these dialects.

These engines are all available free for researchers and the public through the university’s website: www.birzeit.edu.

up
44 users have voted, including you.


Newsletter

Get top stories and blog posts emailed to you each day.

PDF