1.1 Introduction
Information extraction is the task of automatically extracting structured information such as entities, relationships between entities, and attributes describing entities from unstructured and/or semi- structured machine-readable documents. Information extraction task can be viewed from several different views. Some researchers are classified the extraction task according to the information type. The information source can be classified into three main types: free text, structured text and semi-structured text (Lam et al., 2008 and Kaiser et al., 2005). Natural Language Processing (NLP) is used to extract the unrestricted or unregulated type of information like free text and SQL is used to query the structured data which usually is stored in databases (Lam et al., 2008). The wrapper induction system is operated only on highly structured documents (Etzioni et al., 2004). Web page is an example of semi structured text that this survey will explore. The field of information extraction from the web has emerged with the growth of the web.
As a prelude to other parts of this study, this chapter will discuss the background upon which this study was initiated, the statement of problems that led to this study, the Aim and Objectives of the study. Others are Significance of the study, Scope of work, Limitation of the study and Definition of technical terms.
1.2 Background of Study
Information extraction systems are automatically identified and extract factual information related to the events of interest. Also information extraction techniques may be used to learn informative clues of subjectivity (Wiebe et al., 2011). Information extraction systems are targeted towards specific domains of interest and use either manual or semi-automatic learning of the target examples involved. In contrast, the goal of automatic information extraction is to discover the relations among data items of interest and similar data items on a large scale and independent from domain without any needed training (Gatterbauer et al., 2007).
The web is constructed of a huge amount of pages and most of them are generated dynamically from structured data which provides a rich source of usable information to be extracted. The different presentations of information and different formats on each web site is performing a challenge in extraction process and integrating these different sources and formats in one single structured file. Two main markup languages are commonly used in structuring the web content, the Hyper Text Markup Language and Extensible Markup Language (XML). HTML is used to structure the web page content and the XML separates the data structure from layout and provides a much more suitable data representation. Some systems are constructed using XML instead of HTML due to the different presentations of data and different formats used in each web page such as Lixto (Baumgartner et al., 2001). Another important use of XML is for building the web services (Habegger et al., 2004).
The key feature of the web is the redundancy of information which the information can be represent in several different formats on the web from different sources. Most of current methodologies are based on human centred annotation and are often completely manual, so convincing users to annotate documents for the Web is difficult and required a world-wide action of uncertain outcome because the manual annotation is difficult, time consuming and expensive (Ciravegna et al., 2003). Recent researches have focused on extracting information with minimum user intervention. Static annotation associated to a document can be incomplete, incorrect, obsolete (not aligned with pages' updates) or irrelevant for some users. Although the information extraction activity is very complex task, decomposing it into several subtasks can be beneficial for IE main objective. The Information Extraction can be customized according to an application's needs by reordering, selecting and composing some of its tasks. There are some considered tasks like: segmentation, classification, association, normalization and co-reference resolution (Simoes et al., 2009).
1.3 Statement of Problems
Investigation reveals the problems of the Computerized Information Extraction System existing system which are stated as follows; firstly, Incoherent extractions are cases where the extracted relation phrase has no meaningful interpretation. Incoherent extractions arise because the learned extractor makes a sequence of decisions about whether to include each word in the relation phrase, often resulting in incomprehensible relation phrases and secondly, the existing system encounters an uninformative extraction, which occurs when extractions omit critical information.
1.4 Aim and Objectives of Study
The aim of the study is to design and develop a computerized information extraction system. In achieving this aim, the following specific objectives were laid out as follows to design and develop an application system that will:
- Carry out the analysis of manual processes involved in Information Extraction System.
- Extract accurate information according to the data inputted
- Implement the design using Web Based programming languages such as; HTML, CSS, JAVASCRIPT, and PHP.
1.5 Significance of Study
The study will aid in increased efficiency in operation, reducing time and running cost of information processing. Besides, this study is significance because its conclusions would be useful to:
- Human Resources Managers in the hotel and restaurants business
- The Federal, State and Local Government
- Scholars in the field of hotel and restaurant management
This study will be of immense benefit to other researchers who intend to know more on this study and can also be used by non-researchers to build more on their research work. This study contributes to knowledge and could serve as a guide for other study.
1.6 Scope of Study
The study focuses on the Design and Implementation of Computerized Information Extraction System using Jeveniks Restaurant Ltd Enugu State as a case study.
1.7 Limitations of the Study
During the course of this study, many things militated against its completion, some of which are:
- Time Constraint: The time frame given to accomplish this project was very short due to school academic calendar and it was carried out under pressure which made the researcher not to implement some necessary features.
- Establishment Policies: Establishment policies posed a serious limitation as most staffs are not ready to release information needed for this project work. There were lots of information needed from the staffs of this institution to enhance the study which took them time to release or they did not release at all for security purposes, hence the scope was reduced.
- Research material: availability of research material is a major setback to the scope of the study.
- Frequent power failure: This made the researcher append more money on fuel to ensure sustainable power.
- Financial Constraint: Insufficient fund tends to impede the efficiency of the researcher in sourcing for the relevant materials, literature or information and in the process of data collection (internet).
1.8 Definition of Terms
Computer: A computer is an electronic machine that is capable of solving problems by accepting data, performing prescribed operation on the data accepting and supply the result of those operations.
Data: They are values, numbers, quantities or instruction by the computer user. Data are raw facts or figure that are not yet processed.
