1.1 Background of the Study
Alan Turing’s famous article “Computing Machinery and Intelligence” was published, which proposed what is now called the Turing test as a criterion of intelligence. This criterion depends on the ability of a computer program to impersonate a human in a real-time written conversation with a human judge, sufficiently well that the judge is unable to distinguish reliably—on the basis of the conversational content alone—between the program and a real human. The notoriety of Turing’s proposed test stimulated great interest in Joseph Weizenbaum’s program ELIZA, published in 1966, which seemed to be able to fool users into believing that they were conversing with a real human. However Weizenbaum himself did not claim that ELIZA was genuinely intelligent, and the Introduction to his paper presented it more as a debunking exercise.(AlanTuring 1950).
In artificial intelligence … machines are made to behave in wondrous ways, often sufficient to dazzle even the most experienced observer. But once a particular program is unmasked, once its inner workings are explained … its magic crumbles away; it stands revealed as a mere collection of procedures … The observer says to himself “I could have written that”. With that thought he moves the program in question from the shelf marked “intelligent”, to that reserved for curios … The object of this paper is to cause just such a re-evaluation of the program about to be “explained”. Few programs ever needed it more (Weizenbaum, Joseph January 1966).
ELIZA’s key method of operation (copied by chatbot designers ever since) involves the recognition of cue words or phrases in the input, and the output of corresponding pre-prepared or pre-programmed responses that can move the conversation forward in an apparently meaningful way (e.g. by responding to any input that contains the word ‘MOTHER’ with ‘TELL ME MORE ABOUT YOUR FAMILY’). Thus an illusion of understanding is generated, even though the processing involved has been merely superficial. ELIZA showed that such an illusion is surprisingly easy to generate, because human judges are so ready to give the benefit of the doubt when conversational responses are capable of being interpreted as “intelligent”. (WeizenbaumJoseph, January 1966).
Interface designers have come to appreciate that humans’ readiness to interpret computer output as genuinely conversational—even when it is actually based on rather simple pattern-matching—can be exploited for useful purposes. Most people prefer to engage with programs that are human-like, and this gives chatbot-style techniques a potentially useful role in interactive systems that need to elicit information from users, as long as that information is relatively straightforward and falls into predictable categories. Thus, for example, online help systems can usefully employ chatbot techniques to identify the area of help that users require, potentially providing a “friendlier” interface than a more formal search or menu system. This sort of usage holds the prospect of moving chatbot technology from Weizenbaum’s “shelf … reserved for curios” to that marked “genuinely useful computational methods”. (Weizenbaum, 2012)
1.2 Statement of the Problem
The problem faced when searching for a particular context of knowledge might be quite cumbersome. Having to flip through pages of books, and still end up not finding what is needed. While using the internet to search for these things, it could also result to a bunch of unneeded search results, and all of these could be quite frustrating, therefore, the need to have in place a system that could interact with humans, and return the exact desired results.
1.3 Aim and Objectives
The aim of this study is to design and implement a General knowledge chatbot using natural language processing.
The specific objectives are:
- Develop a chatbot that would understand the human language
- Search for answers based on the understanding of the human question
- It reduces the time taken and stress in search for answers on general knowledge
1.4 Significance of the Study
The significance of the study is to leverage on the natural language processing technology to build a platform that eases the search of knowledge on the world wide web through MySQL database.
1.5 Scope of the Study
The scope of this study is centered on design and implementation of general knowledge chatbot using natural language processing for an organization.
1.6 Limitation of the Study
Usually, every work has some limitations and this study is not exempted.The two major limitations of this study are the high programming technique as well as financial constraints. The high programming technique constraint in PHP, JQUERY and MYSQL prevents the researcher to have an in depth study and analysis on the subject matter. While the issue of financial constraint limits the frequency of investigation to/from the institution toward gathering the necessary information relevant for the study.
1.7 Definition of Term
- Chatbot: also known as a smartbots, talkbot, chatterbot, Bot, IM bot, interactive agent, Conversational interface or Artificial Conversational Entity) is a computer program or an artificial intelligence which conducts a conversation via auditory or textual methods. Such programs are often designed to convincingly simulate how a human would behave as a conversational partner, thereby passing the Turing test.
- Natural Language Processing: is a subfield of computer science information engineering and artificial intelligence concerned with the interations between computer and human (natural) langauges, in particular how to program computers to process and analyze large amounts of natural language data.
- Html Code: – HTML stands for Hyper Text Markup Language. It is a type of computer language that is primarily used for files that are posted on the internet and viewed by web browsers. HTML files can also be sent via email.
- Markup Language: – A markup language is a combination of words and symbols which give instructions on how a document should appear. For example, a tag may indicate that words are written in italics or bold type.
- Web Browser: -A Web browser is a software program that interprets the coding language of the World Wide Web in graphic form, displaying the translation rather than the coding. This allows anyone to “browse the Web” by simple point and click navigation, bypassing the need to know commands used in software languages.
- File Extension: – A file extension is the suffix at the end of a filename that tells a computer, and the computer user, which program is needed to open the file. Also called a filename extension, this suffix preceded by at least one period, is generally one to five characters long but the norm is usually three characters in length.
- Email: – Email, also sometimes written as e-mail, is simply the shortened form of electronic mail, a protocol for receiving, sending, and storing electronic messages. Email has gained popularity with the spread of the Internet. In many cases, email has become the preferred method of communication.
- Tcp/Ip: – This often used but little understood set of operations stands for Transmission Control Protocol/Internet Protocol. TCP/IP is the combination of the two and describes the set of protocols that allows hosts to connect to the Internet. In actuality, TCP/IP is a combination of “more than those two protocols, but the TCP and IP parts of TCP/IP are the main ones and the only ones to become part of the acronym that describes the operations involved.
- Text File: – A text file is a computer file that stores a typed document as a series of alphanumeric characters, usually without visual formatting information. The content may be a personal note or list, a journal or newspaper article, a book, or any other text that can be rendered accurately in typewritten form.
- Hyperlink:-A hyperlink is a graphic or a piece of text in an Internet document that can connect readers to another webpage, or another portion of a document. Web users will usually find at least one hyperlink on every webpage. The simplest form of these is called embedded text or an embedded link.
- Utterance: Anything the user says. For example, if a user types “show me yesterday’s financial news”, the entire sentence is the utterance.
- Intent: Intent is the user’s intention. For example, if a user types “show me yesterday’s financial news”, the user’s intent is to retrieve a list of financial headlines. Intents are given a name, often a verb and a noun, such as “showNews”.
- Entity: An entity modifies intent. For example, if a user types “show me yesterday’s financial news”, the entities are “yesterday” and “financial”. Entities are given a name, such as “dateTime” and “newsType”. Entities are sometimes referred to as slots.
- Response: Anything the bot says in response to user input.
- Aiml: Artificial Intelligence Markup Language