Introduction to AI

CT017-3-1 Ver 1.0

Natural Language Processing

 Topic & Structure of the Lesson

• Why NLP is needed?

• NLP used for / NLP mean
• Why NLP difficult
• 4 stages of NLP
• Development of NLP
• Application of NLP
• Hardware and Software issues

CT017-3-1 Introduction to Artificial Intelligence Natural Language Processing Slides

Slide ‹#›2of
of13
37
 Natural Language Processing

• Voice / Speech Recognition

• Text recognition

CT017-3-1 Introduction to Artificial Intelligence Natural Language Processing Slides

Slide ‹#›3of
of13
37
 Why we need NLP?

• The Basics of Natural Language

Processing
https://www.youtube.com/watch?
v=d4gGtcobq8M

CT017-3-1 Introduction to Artificial Intelligence Natural Language Processing Slides

Slide ‹#›4of
of13
37
 NLP mean?

• is a branch of artificial intelligence that deals with the

interaction between computers and humans using the
natural language.
• The ultimate objective of NLP is to read, decipher,
understand, and make sense of the human languages in
a manner that is valuable.
• Most NLP techniques rely on machine learning to derive
meaning from human languages.

CT017-3-1 Introduction to Artificial Intelligence Natural Language Processing Slides

Slide ‹#›5of
of13
37
 Continues

• In fact, a typical interaction between humans and

machines using Natural Language Processing could go
as follows:
1. A human talks to the machine
2. The machine captures the audio
3. Audio to text conversion takes place
4. Processing of the text’s data
5. Data to audio conversion takes place
6. The machine responds to the human by playing the audio file

CT017-3-1 Introduction to Artificial Intelligence Natural Language Processing Slides

Slide ‹#›6of
of13
37
 Do you know you use Natural
Language processing everyday?
1.Autocomplete helps you to suggest rest of the word.
2.Google search’s predictive typing helps you by
suggesting the next word.
3.Spell checker in your email application saves you from
stupid typing errors.
4.Spam detection in your mail box separates spam mails
from important ones.

Over the years there have been many advancements in

Natural language processing.

CT017-3-1 Introduction to Artificial Intelligence Natural Language Processing Slides

Slide ‹#›7of
of13
37
 What is NLP used for?

• Language translation applications such as Google

Translate
• Word Processors such as Microsoft Word and
Grammarly that employ NLP to check grammatical
accuracy of texts.
• Interactive Voice Response (IVR) applications used in
call centers to respond to certain users’ requests.
• Personal assistant applications such as OK Google, Siri,
Cortana, and Alexa.
• NLP vs. NLU: Natural Language Processing vs. Natural Language
Understanding : https://www.youtube.com/watch?v=80_cRqsYycg

CT017-3-1 Introduction to Artificial Intelligence Natural Language Processing Slides

Slide ‹#›8of
of13
37
 Difficulties in NLP

• difficulties in NLP include ambiguity of meaning of words,

• similar sounding words, - bare / bear
• grammar inconsistencies
• Ascent / sarcastic remark to pass information
• and the changing nature of human language

Ex : Meet me at the bank.

• What does this mean – river bank or bank?
Ex : Heavy mental

CT017-3-1 Introduction to Artificial Intelligence Natural Language Processing Slides

Slide ‹#›9of
of13
37
 How does Natural Language
Processing Works?
• NLP entails applying algorithms to identify and extract the natural
language rules such that the unstructured language data is
converted into a form that computers can understand.
• When the text has been provided, the computer will utilize
algorithms to extract meaning associated with every sentence and
collect the essential data from them.
• Sometimes, the computer may fail to understand the meaning of a
sentence well, leading to obscure results.
Here is the biblical sentence that required translation:
• “The spirit is willing, but the flesh is weak.”
• Here is the result when the sentence was translated to Russian and
back to English:
• “The vodka is good, but the meat is rotten.” – AI Winter video Recap

CT017-3-1 Introduction to Artificial Intelligence Natural Language Processing Slides 10of

Slide ‹#› of13
37
 Speech Recognition Systems

• Also known as automatic speech recognition and

computer speech recognition which means
understanding voice by the computer and performing
any required task

• Where are they used for ?

CT017-3-1 Introduction to Artificial Intelligence Natural Language Processing Slides 11of

Slide ‹#› of13
37
 Where can it be used?

• System control / navigation

• Commercial / Industrial application - in car
• Voice dialing

CT017-3-1 Introduction to Artificial Intelligence Natural Language Processing Slides 12of

Slide ‹#› of13
37
 The 4 stages in NLP

CT017-3-1 Introduction to Artificial Intelligence Natural Language Processing Slides 13of

Slide ‹#› of13
37
 Example

• Concept Noun Verb Noun

• Ex : Mary eats Lion

is this correct

CT017-3-1 Introduction to Artificial Intelligence Natural Language Processing Slides 14of

Slide ‹#› of13
37
 Is NLP really AI

• Ability to learn : YES

• Creativity : Yes

• Use of language : YES

• Adapting to new situations : possible

CT017-3-1 Introduction to Artificial Intelligence Natural Language Processing Slides 15of

Slide ‹#› of13
37
 Wordle

• Create wordle – words you have learn so

far
• https://www.bettercloud.com/monitor/the-a
cademy/create-word-cloud-powerpoint-pre
sentation/
• Draw your own wordle – for each chapter
and keep as revision

CT017-3-1 Introduction to Artificial Intelligence Natural Language Processing Slides 16of

Slide ‹#› of13
37
 Case Study

• The Invention And History Of Google |

Silicon Valley: The Untold Story
• https://www.youtube.com/watch?
v=85Nyi4Xb9PY

CT017-3-1 Introduction to Artificial Intelligence Natural Language Processing Slides 17of

Slide ‹#› of13
37
 Google uses this algorithm,

CT017-3-1 Introduction to Artificial Intelligence Natural Language Processing Slides 18of

Slide ‹#› of13
37
 What is Keyword

• Your SEO keywords are the keywords and phrases in

your web content that make it possible for people to find
your site via search engine

• Ex : Buy Laptop in Kuala Lumpur

• Woman education in Malaysia

• Developing a list of keywords in one of the first and most

important steps in any

CT017-3-1 Introduction to Artificial Intelligence Natural Language Processing Slides 19of

Slide ‹#› of13
37
 Keyword (cont)

• You need to know how people are looking for the

product, services, information – that you offer in order to
make it easy fro them to find you.

• Otherwise , they’ll land on one of the many other pages

in the google results. Implement keyword SEO will help
your site rank above your competitor

CT017-3-1 Introduction to Artificial Intelligence Natural Language Processing Slides 20of

Slide ‹#› of13
37
 Keywords

• APU is number 1 IT university in Malaysia.

They have been opened from the year
1993 . APU started off as APIIT name and
now they are a university status. From the
humble beginning they were just a college
in damansara office building. Then they
move to become University college status
– calling themselves – UCTI and now as a
university APU
CT017-3-1 Introduction to Artificial Intelligence Natural Language Processing Slides 21of
Slide ‹#› of13
37
 Google uses semantic network

• Google uses the term knowledge graph

CT017-3-1 Introduction to Artificial Intelligence Natural Language Processing Slides 22of

Slide ‹#› of13
37
 Google (continues)
At the end of 2016 , google
knowledge graph contained
roughly seventhy billion facts
about and relationships
between different entities

https://www.youtube.com/watch?
v=RYc9qbY8aWs

CT017-3-1 Introduction to Artificial Intelligence Natural Language Processing Slides 23of

Slide ‹#› of13
37
 What do you understand with this

CT017-3-1 Introduction to Artificial Intelligence Natural Language Processing Slides 24of

Slide ‹#› of13
37
 How to make in bigger?

• Google Knowledge Graph. Google made this term

popular with the announcement of its knowledge graph
in 2012. However, there are very few technical details
about its organization, coverage and size. There are also
very limited means for using this knowledge graph
outside Google’s own projects.

• What do you think google did?

CT017-3-1 Introduction to Artificial Intelligence Natural Language Processing Slides 25of

Slide ‹#› of13
37
 DBPedia

• DBPedia. This project leverages the structure inherent in

the infoboxes of Wikipedia to create an enormous
dataset of 4.58 things (link
https://wiki.dbpedia.org/about ) and an ontology that has
encyclopedic coverage of entities such as people,
places, films, books, organizations, species, diseases,
etc. This dataset is at the heart of the Open Linked Data
movement. It has been invaluable for organizations to
bootstrap their internal knowledge graphs with millions of
crowdsourced entities.

CT017-3-1 Introduction to Artificial Intelligence Natural Language Processing Slides 26of

Slide ‹#› of13
37
 Goenames

• Geonames. Under a creative commons,

users of Geonames dataset have access
to 25 million geographical entities and
features.

CT017-3-1 Introduction to Artificial Intelligence Natural Language Processing Slides 27of

Slide ‹#› of13
37
 Wordnet

• Wordnet. One of the most well-known

lexical databases for the English
language, providing definitions and
synonyms. Often used to enhance the
performance of NLP and search
applications.

CT017-3-1 Introduction to Artificial Intelligence Natural Language Processing Slides 28of

Slide ‹#› of13
37
 Fact Forge

• FactForge. After years of developing

expertise in the news publishing industry,
Ontotext produced their knowledge graph
of Linked Open Data and news articles
about people, organizations and locations.
It incorporates the data from the KGs
described above as well as specialized
ontologies such as the Financial Industry
Business Ontology.
CT017-3-1 Introduction to Artificial Intelligence Natural Language Processing Slides 29of
Slide ‹#› of13
37
 What are they doing more?

DevFests are community-led developer

events hosted by Google Developer
Groups around the globe. GDGs are
focused on community building and
learning ...

CT017-3-1 Introduction to Artificial Intelligence Natural Language Processing Slides 30of

Slide ‹#› of13
37
CT017-3-1 Introduction to Artificial Intelligence Natural Language Processing Slides 31of
Slide ‹#› of13
37
 Early chatbot

• Early chatbots were primary rule-based, where experts

would encode hundreds of rules mapping what a user
might say, to how a program should reply

• Recap – which chatbot?

• Today – because of memory – train huge number of

sentences with machine learning and make chatbots
better which is customer relationship bot – lot and lots of
recorded samples

CT017-3-1 Introduction to Artificial Intelligence Natural Language Processing Slides 32of

Slide ‹#› of13
37
 Future of google

• https://www.youtube.com/watch?v=oxYhG
VHihnA&t=86s

• What are the areas of new research

CT017-3-1 Introduction to Artificial Intelligence Natural Language Processing Slides 33of

Slide ‹#› of13
37
 Case study 2 : Facebook

• What is facebook -
https://www.youtube.com/watch?v=StPGR
1URK5A

• Facebook chatbot started making its own

language.
• People got scared
https://www.youtube.com/watch?
v=ONPqeHJShdQ

CT017-3-1 Introduction to Artificial Intelligence Natural Language Processing Slides 34of

Slide ‹#› of13
37
 Why Facebook is Investing in
Natural Language Processing
• Facebook has been investing heavily in Natural
Language Processing
• Facebook wants to enable developers to evaluate AI-
based natural-language code search system efficiently.
AI research division released a library of coding
questions with matching answers.
• Facebook AI code-search models available to
programmers. The release also included a training
corpus of more than 4 million Java methods parsed from
over 24,000 GitHub repositories.

CT017-3-1 Introduction to Artificial Intelligence Natural Language Processing Slides 35of

Slide ‹#› of13
37
 Facebook (continue)

• Besides, the effort also indicates artificial intelligence to

support and optimize human labor. AI could make us
better at it
• Facebook form AI Language Research Consortium.

• Representation learning, content understanding, dialog

systems, information extraction, sentiment analysis,
summarization, data collection and cleaning, and speech
translation.
https://www.youtube.com/watch?
v=INnV2VeSBMc
• Facebook PyText NLP framework

CT017-3-1 Introduction to Artificial Intelligence Natural Language Processing Slides 36of

Slide ‹#› of13
37
 Lets discuss

Opinion on facebook
https://www.youtube.com/watch?
v=rkxxeDScKLQ

CT017-3-1 Introduction to Artificial Intelligence Natural Language Processing Slides 37of

Slide ‹#› of13
37
 Conclusion

• Natural Language Processing plays a critical role in

supporting machine-human interactions.
• As more research is being carried in this field, we expect
to see more breakthroughs that will make machines
smarter at recognizing and understanding the human
language.
• Have you used any NLP technique in enhancing the
functionality of your application?

CT017-3-1 Introduction to Artificial Intelligence Natural Language Processing Slides 38of

Slide ‹#› of13
37
 What’s your opinion

• https://www.youtube.com/watch?
v=f9v6givfTEA

CT017-3-1 Introduction to Artificial Intelligence Natural Language Processing Slides 39of

Slide ‹#› of13
37
 https://www.searchengi
nejournal.com/future-of-
enterprise-search/2608
71/

Discuss on Sunday

CT017-3-1 Introduction to Artificial Intelligence Natural Language Processing Slides 40of

Slide ‹#› of13
37
 Tutorial

1. What are the 2 main areas of NLP?

2. Explain the main goal of NLP
3. What must you do before using speech recognition and
roughly how long will it take?
4. Why do we have to go through the process in Q3
5. Name 2 important factor affecting accuracy when using
speech recognition
6. List 4 recommendations when speaking into the
microphone
7. Explain how Speech Recognition can use used to help
the disabled
8. List 3 military uses of speech recognition
CT017-3-1 Introduction to Artificial Intelligence Natural Language Processing Slides 41of
Slide ‹#› of13
37
 9. Explain how Speech technology can be used to allow people who
speak different language to communicate

10. Name one advantage of using handwriting technology rather than a

conventional input method

11. List 2 tips which will improve accuracy when using handwriting
recognition

Upload answer on students tutorial folder – name your doc – with your
name

CT017-3-1 Introduction to Artificial Intelligence Natural Language Processing Slides 42of

Slide ‹#› of13
37
 Question and Answer Session

Q&A

CT017-3-1 Introduction to Artificial Intelligence Natural Language Processing Slides 43of

Slide ‹#› of13
37