Scribd
Upload
27 views22 pages

AI - Lecture 16 - Unit 3 - Chatbots and MT

The document discusses chatbots and machine translation, explaining what chatbots are, their types, and the role of Natural Language Processing (NLP) in enhancing customer interactions. It also covers the challenges faced by chatbots, such as security and sentiment understanding, and outlines various machine translation methods including rule-based, statistical, hybrid, and neural machine translation. The document emphasizes the advantages of NLP and neural machine translation in improving efficiency and accuracy in communication and translation tasks.

Uploaded by

kalashbaisoya
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
27 views22 pages

AI - Lecture 16 - Unit 3 - Chatbots and MT

The document discusses chatbots and machine translation, explaining what chatbots are, their types, and the role of Natural Language Processing (NLP) in enhancing customer interactions. It also covers the challenges faced by chatbots, such as security and sentiment understanding, and outlines various machine translation methods including rule-based, statistical, hybrid, and neural machine translation. The document emphasizes the advantages of NLP and neural machine translation in improving efficiency and accuracy in communication and translation tasks.

Uploaded by

kalashbaisoya
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 22

ARTIFICAL INTELLIGENCE

FOR ENGINEERS (KMC 101)

Unit III:
Lecture 16: Chatbots and Machine
Translation
Outline
• What is Chat bot?
• Need of NLP in Chatbot
• Types of Chatbots
• Working of Chatbots
• Challenges in Chatbots
What is Chat bot?
• A chatbot is a computer program that's designed to
simulate human conversation.
• Users communicate with these tools using a chat
interface or via voice, just like they would converse
with another person.
• Chatbots interpret the words given to them by a
person and provide a pre-set answer.
Use of NLP in Chat bots
• Higher customer satisfaction
▪ NLP helps chatbots understand, analyze and prioritize the questions
according to the complexity & this enables bots to respond to customer
queries faster than a human being.
▪ Active 24 x 7
• Increase in business
▪ Faster responses help in building customer trust and subsequently,
more business.
▪ Reduced cost in customer service
Types of Chat bots
• Rule-based chatbots: These bots simply provide a pre-
defined answer to very specific questions. These bots are great
for things like qualifying leads or offering customers an
interactive FAQ experience.

• NLP based chatbots: These bots combine the benefits of rule-


based bots with the power of intellectually independent
programs to solve user problems. They can remember the
context of conversations and understand user preferences.
These bots use a combination of natural language processing,
machine learning, and AI to understand customers.
Example of Rule based chat bots
• The question, for example: “What is the price of your
membership?”
• The rule-based chatbot is taught how to respond to these
questions—but the wording must be an exact match. This
means manually programming all the different ways to ask
how much a membership costs, for every possible question a
customer may ask, which is incredibly time-consuming.
NLP based chat bots
• NLP based chat bots works off the following
keys:
▪ utterances (ways the user refers to a specific intent)
▪ intent (the meaning behind the words a user types)
▪ entity (details that are important to the intent like
dates and locations)
▪ context (which helps to save and share parameters
across a session), and session (one conversation
from start to finish, even if interrupted).
Example of NLP based chatbot
Example of Rule-based vs NLP
based chatbots
Working of Chat bot
Challenges in Chatbots
• Security: In today’s age of data sensitivity and
privacy, it’s crucial for customers to be able to trust
the bots that they’re giving their information too.
• Voice: Another crucial component of making
chatbots work today is ensuring that they have the
right voice to speak to customers with. Today’s
consumers want bots with certain human elements
like humour and empathy.
• Sentiment: Chatbots need to understand the
sentiment and emotions that today’s customers are
feeling to provide the right kind of service for today’s
consumers.
Machine Translation
• Machine translation is the task of automatically
converting source text in one language to text in
another language.
• It is a process, sometimes referred to as Natural
Language Processing which uses a bilingual data set
and other language assets to build language and
phrase models used to translate text.
Example of Machine Translation
Types of Machine Translation
• Rule-based Machine Translation
• Statistical Machine Translation
• Hybrid method
• Neural Machine Translation
Rule-based Machine Translation
• The system generates sentences in a target language
after analyzing grammatically both the source and the
target languages involved.
• These software programs need language rules and lot
of lexicons(dictionaries) and become efficient after
long term use.
• Ex: Systran
Statistical Machine Translation
• SMT uses statistical models derived from the analysis
of bilingual text corpora usually finding a
correspondence between one word and another.
• SMT developers learned to pattern-match reference
texts to find translations that are statistically most
likely to be suitable.
• These systems train faster than RBMT, provided there
is enough existing language material to reference.
• Ex: Google
Hybrid method

• Hybrid MT is a mix of SMT and RBMT that


also includes a translation memory and thus
produces translations of a better quality.
Rule based vs Statistical
Translation
• Accuracy
▪ SMT can achieve better accuracy/results than RBMT as
can mimic the style of the training data to generate output
based on the frequency of patterns allowing them to
produce more fluent output.
• Training and development cost
▪ SMT’s training and development costs are very high for a
good quality system as they require state-of the-art
computer processing power and storage capacity to build
and manage large translation models.
▪ On the other hand, RBMT systems are built with much less
data (only dictionaries and language rules to translate)
Cont..
• Dynamic and requires less time
▪ RBMT is less dynamic as language is constantly changing,
which means rules must be managed and updated where
necessary in RBMT systems
▪ Whereas SMT systems can be built in much less time and
do not require linguistic experts to apply language rules to
the system.
Neural Machine Translation
• It uses an artificial neural network to predict the likelihood of
a sequence of words, typically modeling entire sentences in a
single integrated model
• Neural MT (NMT) uses machine learning technology for
better accuracy
• This process consumes large amounts of processing power,
and that is why it‘s often run on graphics units of CPUs.
• Google Neural Machine Translation (GNMT) is a neural
machine translation (NMT) system developed
by Google and introduced in November 2016, that uses an
artificial neural network to increase fluency and accuracy
in Google Translate.
Benefits of NMT over SMT
• NMT is based on the model of neural networks in
the human brain, with information being sent to
different “layers” to be processed before output.
• NMT uses deep learning techniques to teach itself to
translate text based on existing statistical models. It
makes for faster translations than the statistical
method and has the ability to create higher quality
output.
• NMT is able to use RNN and LSTM models to learn
linguistic rules. The biggest benefit to NMT is its
speed and quality.
Example of NMT (English to Hindi)

You might also like