Natural Language Processing

Group Members
Muhammad Nofil Bhatty
Hafiz Muhammad Ahmad
Shahrukh Quddus

1
 Natural Language Processing
 Natural Language Processing (NLP) is “ability of
machines to understand and interpret human language
the way it is written or spoken”

 NLP refers to AI method of communicating with an

intelligent systems using a natural language such as
English.
Natural Language Processing
 Why NLP ?
 The objective of NLP is to make computer/machines as
intelligent as human beings in understanding language.

 The ultimate goal of NLP is to the fill the gap how the people
communicate (natural language) and what the computer
understands (machine language).

 NLP can be used to organize and structure knowledge to

perform tasks such as automatic text summarization, translation,
named entity recognition, relationship extraction, sentiment
analysis, speech recognition, and topic segmentation.

 NLP is commonly used for text mining, machine translation, and

automated question answering.
How Computers Understand Language
 Difference Between NLP and Text
Mining
 Natural language processing is responsible for understanding meaning and structure
of given text.
 Text Mining or Text Analytics is a process of extracting hidden information inside
text data through pattern recognition.

 Natural language processing is used to understand the meaning (semantics) of given

text data, while text mining is used to understand structure (syntax) of given text
data.

 As an example - I found my wallet near the bank. The task of NLP is to figure out in
the end that ‘bank’ refers to financial institute or ‘river bank.'
 NLP: Applications
 Summarize blocks of text using Summarizer to extract the most important and
central ideas while ignoring irrelevant information.

 Create a chat bot using Parsey McParseface, a language parsing deep learning model
made by Google that uses Part-of-Speech tagging.

 Automatically generate keyword tags from content using AutoTag, it discovers topics
contained within a body of text.

 Identify the type of entity extracted, such as it being a person, place, or organization
using Named Entity Recognition.

 Use Sentiment Analysis to identify the sentiment of a string of text, from very negative
to neutral to very positive.

 Reduce words to their root, or stem, using PorterStemmer, or break up text into
tokens using Tokenizer.
 Modern Applications
 Search engines
 Google,Yahoo!, Bing, Baidu
 Question answering
 IBM’s Watson
 Natural language assistants
 Apple’s Siri
 Translation systems
 Google Translate
 News digest
 Yahoo!
 Automated earthquake reports
 LA Times
 Automated stock market reports
 Narrative Science
Modern Applications
 Natural Language Processing
 NLP considers the hierarchical structure of language:
several words make a phrase, several phrases make a
sentence and, ultimately, sentences convey ideas,
 KNOWLEDGE IN SPEECH AND LANGUAGE PROCESSING

 Phonetics and Phonology— knowledge about linguistic

sounds
 • Morphology— knowledge of the meaningful
components of words
 • Syntax— knowledge of the structural relationships
between words
 • Semantics—knowledge of meaning
 • Pragmatics— knowledge of the relationship of meaning
to the goals and intentions of the speaker.
 • Discourse— knowledge about linguistic units larger
than a single utterance
Ambiguity and Uncertainty in Language
 Ambiguity, generally used in natural language processing,
can be referred as the ability of being understood in more
than one way.

 Types of Ambiguity:-

 Lexical Ambiguity:-
• The ambiguity of a single word is called lexical ambiguity. For example,
treating the word silver as a noun, an adjective, or a verb.
 Syntactic Ambiguity:-
• This kind of ambiguity occurs when the meaning of the words
themselves can be misinterpreted.
Ambiguity and Uncertainty in Language
 Anaphoric Ambiguity:-
• This kind of ambiguity arises due to the use of anaphora entities in
discourse. For example, the horse ran up the hill. It was very steep. It
soon got tired. Here, the anaphoric reference of “it” in two situations
cause ambiguity.
 Pragmatic Ambiguity:-
• Such kind of ambiguity refers to the situation where the context of a
phrase gives it multiple interpretations. For example, the sentence “I
like you too” can have multiple interpretations like I like you (just like
you like me), I like you (just like someone else does).
NLP Phases
NLP Phases
 Morphological Processing:-
• It is the first phase of NLP. The purpose of this phase is to break
chunks of language input into sets of tokens corresponding to
paragraphs, sentences and words. For example, a word
like “uneasy” can be broken into two sub-word tokens as “un-
easy”.
 Syntax Analysis:-
• It is the second phase of NLP. The purpose of this phase is two folds:
to check that a sentence is well formed or not and to break it up into
a structure that shows the syntactic relationships between the
different words. For example, the sentence like “The school goes
to the boy” would be rejected by syntax analyzer or parser.
NLP Phases
 Semantic Analysis:-
• It is the third phase of NLP. The purpose of this phase is to draw
exact meaning, or you can say dictionary meaning from the text. The
text is checked for meaningfulness. For example, semantic analyzer
would reject a sentence like “Hot ice-cream”.
 Pragmatic Analysis:-
• It is the fourth phase of NLP. Pragmatic analysis simply fits the actual
objects/events, which exist in a given context with object references
obtained during the last phase (semantic analysis). For example, the
sentence “Put the banana in the basket on the shelf” can have two
semantic interpretations and pragmatic analyzer will choose between
these two possibilities.
NLP is Hard
 Understanding natural languages is hard … because of
inherent ambiguity
 Engineering NLP systems is also hard … because of:-
 Huge amount of data resources needed (e.g. grammar, dictionary,
documents to extract statistics from)
 Computational complexity (intractable) of analyzing a
sentence
Ambiguity
“Get the cat with the gloves.”

 There are different types of ambiguity and different

techniques for dealing with it as well
The Bottom Line
 Complete NL Understanding (thus general intelligence) is
impossible.
 But we can make incremental progress.
 Also we have made successes in limited domains.
 [But NLP is costly – Lots of work and resources are
needed, but the amount of return is sometimes not
worth it.]