a survey paper of virtual friend
TRANSCRIPT
[Type text] [Type text] [Type text]
A Survey Paper of Virtual Friend Chatbot
Siddiq Abu Bakkar [09-13368-1] AMERICAN INTERNATIONAL UNIVERSITY BANGLADESH (AIUB)
CSE DEPARTMENT
[email protected] ; [email protected]
2012
Shaon [Type the company name]
3/20/2012
1 | P a g e
Virtual Friend Chatbot Siddiq Abu Bakkar 09-13368-1
A Survey Paper of Virtual Friend Chatbot
Siddiq Abu Bakkar
09-13368-1 AMERICAN INTERNATIONAL UNIVERSITY BANGLADESH (AIUB)
CSE DEPARTMENT
[email protected] ; [email protected]
Abstract:
A chatter robot, chatterbot , chatbot or chat bot is a computer
program designed to simulate an intelligent conversation with one or more human users via auditory or textual
methods, primarily for engaging in small talk. The primary aim of such simulation
has been to fool the user into thinking that the program's output has been produced by a human (the Turing test). Programs
playing this role are sometimes referred to as Artificial Conversational Entities, talk
bots or chatterboxes. In addition, however, chatterbots are often integrated into dialog systems for various practical purposes
such as online help, personalized service, or information acquisition. Some
chatterbots use sophisticated natural language processing systems, but many simply scan for keywords within the input
and pull a reply with the most matching keywords, or the most similar wording
pattern, from a textual database.
Virtual Friend (VF) is a computer
program and early example of primitive natural language processing. VF operated
by processing user's response to scripts, the most famous of which was DOCTOR, a simulation of a Rogerian
psychotherapist. Eliza, using almost no information about human thought or
emotion, DOCTOR sometimes provided a startlingly human-like interaction .Eliza was written at MIT by Joseph
Weizaenbaum between 1964 and 1966.
When the ―USER‖ exceeded the
very small knowledge base, VF might provide a generic response, for example, responding to ―I won't go to university
today.‖ with ―Why you won't go to university, are you feeling sick?‖. The
response to ―Yahoo! I have got 3.94 CGPA in this semesters. ‖ would be ―Congratulation!! I am very much happy
for your excellent result.‖ VF is implemented using simple pattern
matching techniques, but is taken seriously by several of it users, even after explained to them how it worked.
Virtual Friend Response
2 | P a g e
Virtual Friend Chatbot Siddiq Abu Bakkar 09-13368-1
The program was designed to showcase the digitized voices the cards
were able to produce, though the quality was far from life-like. Its AI engine was likely based on something similar to
the ELIZA algorithm.
Contents:
1. Natural Language Processing
[NLP] 2. Machine Learning [ML]
I. Supervised learning
algorithms II. Logic based algo-
rithms
Decision
trees
III. Statistical learning
algorithms
Naive Bayes classifiers
Bayesian Networks
3. Speech Recognition [SR]
4. Turing Test [TT]
5. Most Popular Chatbots
a. ELIZA
b. PARRY
c. The Chinese Room
d. SIRI
i. Details of SIRI
ii. Reception Of SIRI
iii. SIRI says some weird things
6. References.
Natural Language Processing:
The history of machine translation
dates back to the seventeenth century, when philosophers such
as Leibniz and Descartes put forward proposals for codes which would relate words between languages. All of these
proposals remained theoretical, and none resulted in the development of an actual
machine.
The first patents for "translating
machines" were applied for in the mid-
1930s. One proposal, by Georges
Artsrouni was simply an automatic
bilingual dictionary using paper tape. The
other proposal, by Peter Troyanskii,
a Russian, was more detailed. It included
both the bilingual dictionary, and a method
for dealing with grammatical roles
between languages, based on Esperanto.
In 1950, Alan Turing published his
famous article "Computing Machinery and
Intelligence"[1] 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.
In 1957, Noam
Chomsky’s Syntactic
Structures revolutionized Linguistics with
'universal grammar', a rule based system of
syntactic structures. However, the real
progress of NLP was much slower, and
after the ALPAC report in 1966, which
found that ten years long research had
failed to fulfill the expectations, funding
was dramatically reduced internationally.
In 1969 Roger Schank introduced
the conceptual dependency theory for
natural language understanding. This
3 | P a g e
Virtual Friend Chatbot Siddiq Abu Bakkar 09-13368-1
model, partially influenced by the work
of Sydney Lamb, was extensively used by
Schank's students at Yale University, such
as Robert Wilensky, Wendy Lehnert,
andJanet Kolodner.
In 1970, William A. Woods
introduced the augmented transition
network (ATN) to represent natural
language input. Instead of phrase structure
rules ATNs used an equivalent set of finite
state automata that were called recursively.
ATNs and their more general format called
"generalized ATNs" continued to be used
for a number of years.
Machine Learning:
There are several applications for
Machine Learning (ML), the most signifi-cant of which is data mining. People are
often prone to making mistakes duringanalyses or, possibly, when trying to establish Relationships between multiple
features. This makes it difficult for them to find solutions to certain problems. Ma-
chine learning can often be successfully applied to these problems, improving the efficiency of systems and the designs of
machines. Every instance in any dataset used
by machine learning algorithms is repre-sented using the same set of features. The features may be continuous, categorical or
binary. If instances are given with known labels (the corresponding correct outputs)
then the learning is called supervised, in contrast to unsupervised learning, where instances are unlabeled. By applying these
unsupervised (clustering) algorithms, re-searchers hope to discover unknown, but
useful, classes of items (Jain et al., 1999). Another kind of machine learning
is reinforcement learning (Barto & Sutton,
1997). The training information provided to the learning system by the environment
(external trainer) is in the form of a scalar reinforcement signal that constitutes a measure of how well the system operates.
The learner is not told which actions to
take, but rather must discover which ac-tions yield the best reward, by trying each
action in turn.
Numerous ML applications involve tasks that can be set up as supervised. In the present paper, we have concentrated on
the techniques necessary to do this. In par-ticular, this work is concerned with classi-
fication problems in which the output of instances admits only discrete, unordered values. Instances with known labels (the
corresponding correct outputs) We have limited our references to recent
refereed journals, published books and conferences. In addition, we have added some references regarding the original
work that started the particular line of re-search under discussion. A brief review of
what ML includes can be found in (Dutton & Conroy, 1996). De Mantaras and Ar-mengol (1998) also presented a historical
survey of logic and instance based learning classifiers. The reader should be cautioned
that a single article cannot be a compre-hensive review of all classification learn-ing algorithms. Instead, our goal has been
to provide a representative sample of exist-ing lines of research in each learning tech-
nique. In each of our listed areas, there are many other papers that more comprehen-sively detail relevant work.
Supervised learning algorithms
Inductive machine learning is the
process of learning a set of rules from in-stances (examples in a training set), or more generally speaking, creating a classi-
fier that can be used to generalize from new instances. The process of applying
supervised ML to a real-world problem is described in Figure
4 | P a g e
Virtual Friend Chatbot Siddiq Abu Bakkar 09-13368-1
Figure: The process of supervised ML
The first step is collecting the da-
taset. If a requisite expert is available, then s/he could suggest which fields (attributes, features) are the most informative. If not,
then the simplest method is that of ―brute-force,‖ which means measuring everything
available in the hope that the right (in-formative, relevant) features can be isolat-ed. However, a dataset collected by the
―brute-force‖ method is not directly suita-ble for induction. It contains in most cases
noise and missing feature values, and therefore requires significant pre-processing (Zhang et al., 2002).
The second step is the data prepara-
tion and data preprocessing. Depending on the circumstances, researchers have a number of methods to choose from to han-
dle missing data (Batista & Monard, 2003). Hodge & Austin (2004) have re-
cently introduced a survey of contempo-rary techniques for outlier (noise) detec-tion. These researchers have identified the
techniques’ advantages and disadvantages. Instance selection is not
only used to handle noise but to cope with the infeasibility of learning from very
large datasets. Instance selection in these datasets is an optimization problem that
attempts to maintain the mining quality while minimizing the sample size (Liu and Motoda, 2001). It reduces data and enables
a data mining algorithm to function and work effectively with very large datasets.
There is a variety of procedures for sam-pling instances from a large dataset (Reinartz, 2002). Feature subset selection
is the process of identifying and removing as many irrelevant and redundant features
as possible (Yu & Liu, 2004). This reduces the dimensionality of the data and enables data mining algorithms to operate faster
and more effectively. The fact that many features depend on one another often
unduly influences the accuracy of super-vised ML classification models. This prob-lem can be addressed by constructing new
features from the basic feature set (Mar-kovitch & Rosenstein, 2002). This tech-
nique is called feature construc-tion/transformation. These newly generat-ed features may lead to the creation of
more concise and accurate classifiers. In addition, the discovery of meaningful fea-
tures contributes to better comprehensibil-ity of the produced class.
Logic based algorithms:
Decision trees: Murthy (1998) provided an over-
view of work indecision trees and a sample of their usefulness to newcomers as well as
practitioners in the field of machine learn-ing. Thus, in this work, apart from a brief description of decision trees, we will refer
to some more recent works than those in Murthy’s article as well as few very im-
portant articles that were published earlier. Decision trees are trees that classify in-stances by sorting them based on feature
values. Each node in a decision tree repre-sents a feature in an instance to be classi-
fied, and each branch represents a value
5 | P a g e
Virtual Friend Chatbot Siddiq Abu Bakkar 09-13368-1
that the node can assume. Instances are classified starting at the root node
and sorted based on their feature values. Figure is an example of a decision tree for
the training set of Table.
Using the decision tree depicted in Figure as an example, the instance ⟨at1 = a1, at2 =
b2, at3 = a3, at4 =b4⟩nodes: at1, at2, and finally at3, which would classify the instance as being posi-
tive (represented by the values ―Yes‖). The problem of constructing optimal binary
decision trees is an NPcomplete problem and thus theoreticians have searched for efficient heuristics for constructing
near-optimal decision trees.
Statistical Learning Algorithms:
Conversely to ANNs, statistical
approaches are characterized by having an explicit underlying probability model,
which provides a probability that an instance belongs in each class, rather than simply a classification. Linear discriminant
analysis (LDA) and the related Fisher's linear discriminant are simple methods
used in statistics and machine learning to find the linear combination of features
which best separate two or more classes of object (Friedman, 1989). LDA works when the measurements made on each ob-
servation are continuous quantities. When dealing with categorical variables, the
equivalent technique is Discriminant Correspondence Analysis (Mika et al.1999). Maximum entropy is another
general technique for estimating probabil-ity distributions from data. The overriding
principle in maximum entropy is that when nothing is known, the distribution should be as uniform as possible, that is, have
maximal entropy. Labeled training data is used to derive a set of constraints for the
model that characterize the class-specific expectations for the distribution. Csiszar (1996) provides a good tutorial introduc-
tion to maximum entropy techniques. Bayesian networks are the most well-
known representative of statistical learning algorithms. A comprehensive book on Bayesian networks is Jensen’s
(1996). Thus, in this study, apart from our brief description of Bayesian networks, we
mainly refer to more recent works.
Naive Bayes classifiers:
Naive Bayesian networks (NB) are
very simple Bayesian networks which are composed of directed acyclic graphs with only one parent (representing the unob-
served node) and several children (corre-sponding to observed nodes) with a strong
assumption of independence among child nodes in the context of their parent (Good, 1950).Thus, the independence model
(Naive Bayes) is based on estimating (Nilsson, 1965):
R= ( ) ( )
( ) ( ) ( ) ( )
6 | P a g e
Virtual Friend Chatbot Siddiq Abu Bakkar 09-13368-1
( ) ( ) ( ) ( )
| | | | | |
r r P i X P i P X i P i P X i
P j X P j P X j P j P X j = = ΠΠ
Comparing these two probabilities, the larger probability indicates that the class label value that is more likely to be
the actual label (if R>1: predict i predict j). Cestnik et al (1987) first used
the Naive Bayes in ML community. Since the Bayes classification algorithm uses a product operation to compute the probabil-
ities P(X, i), it is especially prone to being unduly impacted by probabilities of 0. This
can be avoided by using Laplace estimator or m-esimate, by adding one to all numera-tors and adding the number of added ones
to the denominator (Cestnik, 1990).
The assumption of independence among child nodes is clearly almost al-ways wrong and for this reason naive
Bayes classifiers are usually less accurate that other more sophisticated learning al-
gorithms (such ANNs). However, Domingos & Pazzani
(1997) performed a large-scale comparison of the naive Bayes classifier with state-of-
the-art algorithms for decision tree induc-tion, instance-based learning, and rule in-duction on standard benchmark datasets,
and found it to be sometimes superior to the other learning schemes, even on da-
tasets with substantial feature dependen-cies.
The basic independent Bayes mod-
el has been modified in various ways in attempts to improve its performance. At-
tempts to overcome the independence assumption are mainly based on adding extra edges to include some of the depend-
encies between the features, for example (Friedman et al. 1997). In this case, the
network has the limitation that each fea-ture can be related to only one other fea-
ture. Semi-naive Bayesian classifier is an-other important attempt to avoid the
independence assumption. (Kononenko, 1991), in which attributes are partitioned into groups and it is assumed that xi is
conditionally independent of xj if and only if they are in different groups.
The major advantage of the naive
Bayes classifier is its short computational
time for training. In addition, since the model has the form of a product, it can be
converted into a sum through the use of logarithms – with significant consequent computational advantages. If a feature is
numerical, the usual procedure is to discre-tize it during data pre-processing (Yang &
Webb, 2003), although a researcher can use the normal distribution to calculate probabilities (Bouckaert, 2004).
Bayesian Networks: A Bayesian Network (BN) is a
graphical model for probability relation-
ships among a set of variables (features). The Bayesian network structure S is a di-
rected acyclic graph (DAG) and the nodes in S are in one-to-one correspondence with the features X. The arcs represent casual
influences among the features while the lack of possible arcs in S encodes condi-
tional independencies. Moreover, a feature (node) is conditionally independent from its non-descendants given its parents (X1 is
conditionally independent from X2 given X3 if P(X1|X2,X3)=P(X1|X3) for all possi-
ble values of X1, X2, X3).
Speech recognition:
In Computer Science, Speech
recognition is the translation of spoken words into text. It is also known as
"automatic speech recognition", "ASR", "computer speech recognition", "speech to text", or just "STT".
7 | P a g e
Virtual Friend Chatbot Siddiq Abu Bakkar 09-13368-1
Speech Recognition is technology
that can translate spoken words into
text. Some SR systems use "training"
where an individual speaker reads sections
of text into the SR system. These systems
analyze the person's specific voice and use
it to fine tune the recognition of that
person's speech, resulting in more accurate
transcription. Systems that do not use
training are called "Speaker Independent"
systems. Systems that use training are
called "Speaker Dependent" systems.
Speech recognition applications
include voice user interfaces such as voice
dialing (e.g., "Call home"), call routing ("I
would like to make a collect
call"), demotic appliance control, search
(e.g., find a podcast where particular
words were spoken), simple data entry
(e.g., entering a credit card number),
preparation of structured documents (e.g.,
a radiology report), speech-to-text
processing (e.g., word
processors or emails), and aircraft (usually
termed Direct Voice Input).
The term voice recognition refers
to finding the identity of "who" is
speaking, rather than what they are
saying. Recognizing the speaker voice
recognition can simplify the task of
translating speech in systems that have
been trained on specific person's voices or
it can be used to authenticate or verify the
identity of a speaker as part of a security
process. "Voice recognition" means
"recognizing by voice", something humans
do all the time over the phone. As soon as
someone familiar says "hello" the listener
can identify them by the sound of their
voice alone.
Turing Test:
The Turing test is a test of
a machine's ability to exhibit intelligent
behavior. In Turing's original illustrative
example, a human judge engages in a natural language conversation with a human and a machine designed to
generate performance indistinguishable from that of a human being. All
participants are separated from one another. If the judge cannot reliably tell the
machine from the human, the machine is said to have passed the test. The test does not check the ability to give the correct
answer; it checks how closely the answer resembles typical human answers. The
conversation is limited to a text-only channel such as a computer keyboard and screen so that the result is
not dependent on the machine's ability to render words into audio.
The test was introduced by Alan
Turing in his 1950 paper Computing Machinery and Intelligence, which opens
with the words: "I propose to consider the question, 'Can machines think?'" Since "thinking" is difficult to define, Turing
chooses to "replace the question by another, which is closely related to it and
is expressed in relatively unambiguous words." Turing's new question is: "Are there imaginable digital computers which
would do well in the imitation game?" This question, Turing believed, is
one that can actually be answered. In the remainder of the paper, he argued against all the major objections to the proposition
that "machines can think".
8 | P a g e
Virtual Friend Chatbot Siddiq Abu Bakkar 09-13368-1
ELIZA and PARRY
In 1966, Joseph
Weizenbaum created a program which
appeared to pass the Turing test. The
program, known as ELIZA, worked by
examining a user's typed comments for
keywords. If a keyword is found, a rule
that transforms the user's comments is
applied, and the resulting sentence is
returned. If a keyword is not found, ELIZA
responds either with a generic riposte or by
repeating one of the earlier comments. In
addition, Weizenbaum developed ELIZA
to replicate the behaviour of a Rogerian
psychotherapist, allowing ELIZA to be
"free to assume the pose of knowing
almost nothing of the real world." With
these techniques, Weizenbaum's program
was able to fool some people into
believing that they were talking to a real
person, with some subjects being "very
hard to convince that ELIZA
is nothuman." Thus, ELIZA is claimed by
some to be one of the programs (perhaps
the first) able to pass the Turing
Test, although this view is highly
contentious (see below).
Kenneth Colby created PARRY in
1972, a program described as "ELIZA with
attitude".[26] It attempted to model the
behaviour of a paranoidschizophrenic,
using a similar (if more advanced)
approach to that employed by
Weizenbaum. In order to validate the
work, PARRY was tested in the early
1970s using a variation of the Turing Test.
A group of experienced psychiatrists
analysed a combination of real patients
and computers running PARRY
through teleprinters. Another group of 33
psychiatrists were shown transcripts of the
conversations. The two groups were then
asked to identify which of the "patients"
were human and which were computer
programs. The psychiatrists were able to
make the correct identification only 48 per
cent of the time — a figure consistent with
random guessing.
In the 21st century, versions of
these programs (now known as
"chatterbots") continue to fool people.
"CyberLover", a malware program, preys
on Internet users by convincing them to
"reveal information about their identities
or to lead them to visit a web site that will
deliver malicious content to their
computers".The program has emerged as a
"Valentine-risk" flirting with people
"seeking relationships online in order to
collect their personal data".
The Chinese Room
Main article: Chinese room
John Searle's 1980 paper Minds,
Brains, and Programs proposed an
argument against the Turing Test known as
the "Chinese room" thought experiment.
Searle argued that software (such as
ELIZA) could pass the Turing Test simply
by manipulating symbols of which they
had no understanding. Without
understanding, they could not be described
as "thinking" in the same sense people do.
Therefore—Searle concludes—the Turing
Test cannot prove that a machine can
think. Searle's argument has been widely
criticized, but it has been endorsed as well.
Arguments such as that proposed
by Searle and others working on
the philosophy of mind sparked off a more
intense debate about the nature of
intelligence, the possibility of intelligent
machines and the value of the Turing test
that continued through the 1980s and
1990s.
9 | P a g e
Virtual Friend Chatbot Siddiq Abu Bakkar 09-13368-1
Siri (Speech Interpretation and Recognition Interface)
Siri (Speech Interpretation and Recognition Interface)
(pronounced /ˈsɪri/) is an intelligent personal assistant and knowledge
navigator which works as an application for Apple's iOS. The application uses a natural language user interface to answer
questions, make recommendations, and perform actions by delegating requests to a
set of web services. Apple claims that the software adapts to the user's individual preferences over time and personalizes
results, and performing tasks such as finding recommendations for nearby
restaurants, or getting directions.
Siri was originally introduced as an
iOS application available in the App
Store by Siri Inc. Siri Inc. was acquired by
Apple on April 28, 2010. Siri Inc. had
announced that their software would be
available for BlackBerry and for Android-
powered phones, but all development
efforts for non-Apple platforms were
cancelled after the acquisition by Apple.
Siri is now an integral part of iOS
5, and available only on the iPhone 4S,
launched on October 4, 2011. Despite this,
hackers were able to adapt Siri in prior
iPhones. On November 8, 2011, Apple
publicly announced that it had no plans to
support Siri on any of its older devices.
Siri Inc. was founded in 2007
by Dag Kittlaus (CEO), Adam Cheyer (VP
Engineering), andTom Gruber (CTO/VP
Design), together with Norman Winarsky
from SRI International's venture group. On
October 13, 2008, Siri announced it had
raised an $8.5 million Series A financing
round, led by Menlo
Ventures and Morgenthaler Ventures. In
November 2009, Siri raised a $15.5
million Series B financing round from the
same investors as in their previous round,
but led by Hong-Kong billionaire Li Ka-
shing. Dag Kittlaus left his position as
CEO of Siri at Apple after the launch of
the iPhone 4S.
Reception Of Siri:
Siri was met with a very positive
reaction for its ease of use and practicality,
as well as its apparent
"personality". Google’s executive
chairman and former chief, Eric Schmidt,
has conceded that Siri could pose a
"competitive threat" to the company’s core
search business. Google generates a large
portion of its revenue from clickable ad
links returned in the context of searches.
The threat comes from the fact that Siri is
a non-visual medium, therefore not
affording users with the opportunity to be
exposed to the clickable ad links. Writing
in The Guardian, journalist Charlie
Brooker described Siri's tone as "servile"
while also noting that it worked
"annoyingly well."
However, Siri was criticized by
organizations such as the American Civil
Liberties Union and NARAL Pro-Choice
10 | P a g e
Virtual Friend Chatbot Siddiq Abu Bakkar 09-13368-1
America after users found that it would not
provide information about the location of
birth control or abortion providers,
sometimes directing users to anti-
abortion crisis pregnancy centers instead.
Apple responded that this was a glitch
which would be fixed in the final version.
It was suggested that abortion providers
could not be found in a Siri search because
they did not use "abortion" in their
descriptions. At the time the controversy
arose, Siri would suggest locations to buy
illegal drugs, hire a prostitute, or dump a
corpse, but not find birth control or
abortion services. Apple responded that
this behavior is not intentional and will
improve as the product moves from beta to
final product.
Siri has not been well received by
some English speakers with distinctive
accents, including Scottish and Americans
from Boston or the South. Apple's Siri
FAQ states that, "as more people use Siri
and it’s exposed to more variations of a
language, its overall recognition of dialects
and accents will continue to improve, and
Siri will work even better."
Despite many functions still requiring the
use of the touchscreen, the National
Federation of the Blind describes the
iPhone as "the only fully
accessible handset that a blind person can
buy".
11 | P a g e
Virtual Friend Chatbot Siddiq Abu Bakkar 09-13368-1
Siri says some weird things
t
ex
Si
ri
s
ay
s
som
e
we
ir
d
th
ing
s
12 | P a g e
Virtual Friend Chatbot Siddiq Abu Bakkar 09-13368-1
References:
1. http://en.wikipedia.org/wiki/H
istory_of_Natural_language_processing
2. http://en.wikipedia.org/wiki/N
atural_language_processing
3. http://research.microsoft.com/en-us/groups/nlp/
4. http://www.mitpressjournals.o
rg/doi/abs/10.1162/coli.2000.27.4.602
5. http://see.stanford.edu/see/courseinfo.aspx?coll=63480b48-8819-
4efd-8412-263f1a472f5a
6. http://www.cs.uccs.edu/~kalita/reu.html
7. http://en.wikipedia.org/wiki/S
upervised_learning
8. http://www.mathworks.com/help/toolbox/stats/bsvjxt5-1.html
9. http://www.gabormelli.com/RKB/Supervised_Learning_Algorith
m
10. http://en.wikipedia.org/wiki/Decision_tree
11. http://en.wikipedia.org/wiki/D
ecision_tree_learning
12. http://en.wikipedia.org/wiki/Naive_Bayes_classifier
13. http://www.statsoft.com/textbook/naive-bayes-classifier/
14. http://bionicspirit.com/blog/20
12/02/09/howto-build-naive-bayes-classifier.html
15.
http://en.wikipedia.org/wiki/Bayesian_network
16. http://research.microsoft.com/
apps/pubs/default.aspx?id=69588
17. http://www.norsys.com/tutorials/netica/nt_toc_A.htm
18. http://www.artificial-solutions.com/products/virtual-
assistant/virtual-assistant-automated-speech-recognition/
19. http://en.wikipedia.org/wiki/S
peech_Recognition
20. http://articles.latimes.com/2011/dec/04/business/la-fi-voice-flubs-
20111204 21. http://www.chatbots.org/featur
es/speech_recognition/
22. http://en.wikipedia.org/wiki/List_of_chatterbots
23. http://en.wikipedia.org/wiki/T
uring_test
24. http://www.webopedia.com/TERM/
T/Turing_test.html
25. http://en.wikipedia.org/wiki/E
13 | P a g e
Virtual Friend Chatbot Siddiq Abu Bakkar 09-13368-1
LIZA
26. http://nlp-addiction.com/eliza/
27. http://www-ai.ijs.si/eliza-cgi-bin/eliza_script
28. http://en.wikipedia.org/wiki/P
ARRY
29. http://www.chatbots.org/chatbot/parr
y/
30. http://en.wikipedia.org/wiki/Racter
31. http://en.wikipedia.org/wiki/Mark_V_Shaney
32. http://nlp-
addiction.com/chatbot/
33. http://www.chatbots.org/
34. http://www.simonlaven.com/
35. http://www.esotericarticles.com/list_of_chatterbots.html
36. http://www.chatterbotcollection.com/category_contents.php?id_cat
=70
37. http://www.chatterbotcollection.com/item_display.php?id=2954
38. http://en.wikipedia.org/wiki/C
hatterbot
39. http://en.wikipedia.org/wiki/Siri_(software)
40. http://www.apple.com/iphone/features/siri.html
41. http://www.theverge.com/201
1/10/12/2486618/siri-weird-iphone-4s
42. http://lifehacker.com/5846543/all-about-siri-your-iphones-new-
assistant
43. Supervised Machine Learning Survey Paper
44. Survey of Artificial
Intelligence for Prognostic 45. A SURVEY ON ARTIFICIAL
INTELLIGENCE BASED BRAIN PATHOLOGY
IDENTIFICATION TECHNIQUES IN
MAGNETIC RESONANCE IMAGES
46. http://dx.doi.org/10.1145%2F
365153.365168
47. http://en.wikipedia.org/wiki/Turing_test#cite_noteFOOTNOTEWeizenbaum196637-22
48. http://en.wikipedia.org/wiki/T
uring_test#cite_note-FOOTNOTEWeizenbaum196642-
23
49. http://en.wikipedia.org/wiki/Eric_Schmidt
50. http://www.norsys.com/tutoria
ls/netica/nt_toc_A.htm