Paper—Employing Information Extraction for Building Mobile Applications Employing Information Extraction for Building Mobile Applications https://doi.org/10.3991/ijim.v11i2.6569 Daoud M. Daoud Princess Sumaya University for Technology (PSUT), Jordan d.daoud@psut.edu.jo M. Samir Abou El-Seoud The British University in Egypt (BUE), Egypt selseoud@yahoo.com Abstract—We describe a SMS-based information system called CATS, which allows posting and searching through free Arabic text using Information Extraction (IE) technology. We discuss the challenges of applying IE technolo- gy for unedited real Arabic text. In addition, we describe the structure of this system and our approach to produce an open robust system capable of including more sub domains with the minimum effort. Keywords—Information Extraction, Arabic Language Processing, Classified Ads, Attribute Based Searching. 1 Introduction Natural language is considered the simplest technique of human-machine interac- tion. It is suitable for naïve users who know the task domain well. However, building a robust commercial application that employs natural language requires restricted domain where we have control over linguistic and world knowledge. Information Extraction (IE) is a comparatively new technology within the more general field of Natural Language Processing. IE is the process of identifying relevant information where the criteria for relevance are predefined by the user in the form of a template that is to be filled [9]. The current development in the field of IE can be followed in to the Message Understanding Conferences (MUCs). In this competition English has always been the unique target language, with the exception of MUC-6 (MET-1), where Spanish and Chinese were considered as well [10]. IE systems are usually designed for a specific domain, and the types of facts to be extracted are de- fined in advance [11]. Most of the researchers believe that the IE technology is prom- ising and pertinent to a wide range of fields, much of the research have been directed toward news items found in the web. IE systems are a key factor in encouraging NLP researchers to move from small-scale systems and artificial data to large-scale sys- tems operating on human [7]. iJIM ‒ Vol. 11, No. 2, 2017 99