How expert explains Natural Language Processing!

Here, is all about how expert explains NLP(Natural Language Processing). Dr. BAL KRISHNA BAL Associate Professor of Computer Science Kathmandu Unversity Dhulikhel, He works on natural language processing and computation linguistic. The article is based on his explanation about NLP in a virtual session.

How expert explains Natural Language Processing Bal Krishna Bal
Dr. Bal Krishna Bal

Content

  • what is NLP
  • Use Case of NLP
  • Why is NLP difficult
  • How Does NLP work
  • What is the technique used in NLP
  • Some frequently used algorithm and model
  • What is the best NLP approach
  • Some NLP application
  • NLP resources

What is NLP?

How expert explains Natural Language Processing ->What is NLP
What is NLP

Branch of AI that deals with the interaction between computers and humans using the natural language, or language spoken by humans.

  • The ultimate objective of NLP is:
  • Read
  • Decipher
  • Understand
  • Make sense of the human language in a manner that is valuable

Use case

How expert explains Natural Language Processing->Use case of NLP
Use case of NLP
  • Clinical NLP
  • Sentiment Analysis
  • Spam Email Filtering
  • Fake News Detection
  • Voice-Driven Interfaces

How Does NLP Works?

How expert explains Natural Language Processing->Working pipeline of NLP
working pipeline of NLP
Word Segmentation

Breaking a string of characters (graphemes) into a sequence of words. In some written languages (e.g. Chinese) words are not separated by spaces. Even in English, characters other than white-space can be used to separate words [e.g. , ; . – : ( ) ]

Examples from English URLs:

jumptheshark.com => jump the shark .com

myspace.com/pluckerswingbar

=>myspace .com pluckers wing bar

=>myspace .com plucker swing bar

Morphological Analysis

Morphology is the field of linguistics that studies the internal structure of words. A morpheme is the smallest linguistic unit that has semantic meaning

e.g. β€œcarry”, β€œpre”, β€œed”, β€œly”, β€œs”

It is the task of segmenting a word into its morphemes:

carried => carry + ed (past tense)

independently =>in + (depend + ent) + ly

Googlers => (Google + er) + s (plural)

unlockable  => un + (lock + able) ?

=>(un + lock) + able ?

Part of Speech Tagging

Annotate each word in a sentence with a part-of-speech

I ate the spaghetti with meatballs.

Pro V Det N Prep N

John saw the saw and decided to take it to the table.

PN V Det N Con V Part V Pro Prep Det N

Useful for subsequent syntactic parsing and word sense disambiguation.


Phrase Chunking

Find all non-recursive noun phrases (NPs) and verb phrases (VPs) in a sentence.

[NP I] [VP ate] [NP the spaghetti] [PP with] [NP meatballs].

[ NP He ] [VP reckons ] [NP the current account deficit ] [VP will narrow ] [PP to ] [NP only # 1.8 billion ] [PP in ] [NP September ]

Syntactic Parsing

Produce the correct syntactic parse tree for a sentence.

How expert explains Natural Language Processing -> syntatic parsing
Syntactic Parsing


Word Sense Disambiguation
  • Words in natural language usually have a fair number of different possible meanings.

Ellen has a strong interest in computational linguistics.

Ellen pays a large amount of interest on her credit card.

  • For many tasks (question answering, translation), the proper sense of each ambiguous word in a sentence must be determined.
Semantic Role Labeling (SRL)

β€’ For each clause, determine the semantic role played by each noun phrase that is an argument to the verb.

agent patient source destination instrument

John drove Mary from Austin to Dallas in his Toyota Prius.

The hammer broke the window.

β€’ Also referred to a β€œcase role analysis,” β€œthematic analysis,” and β€œshallow semantic parsing”

Semantic Parsing
  • A semantic parser maps a natural-language sentence to a complete, detailed semantic representation (logical form).
  • For many applications, the desired output is immediately executable by another program.
  • Example: Mapping an English database query to Prolog:

How many cities are there in the US?

answer(A, count(B, (city(B), loc(B, C), const(C, countryid(USA))), A))

Pragmatics/Discourse
  • Anaphora resolution/Co-reference
  • Determine which phrases in a document refer to the same underlying entity.

John put the carrot on the plate and ate it.

Bush started the war in Iraq. But the president needed the consent of Congress.

β€’ Some cases require difficult reasoning.

Today was Jack’s birthday. Penny and Janet went to the store. They were going to get presents. Janet decided to get a kite. “Don’t do that,” said Penny. “Jack has a kite. He will make you take it back.”

Pragmatics/Discourse
  • Ellipsis Resolution

Frequently words and phrases are omitted from sentences when they can be inferred from context.

“Wise men talk because they have something to say; fools, because they have to say something.β€œ (Plato)

“Wise men talk because they have something to say; fools talk because they have to say something.β€œ (Plato)

Some Frequently used Algorithms and Model
  • Tokenization
  • Stemming
  • Lemmatization
  • Bag of Words Model
  • Stop Words Removal
  • Term Frequency – Inverse
  • Document Frequency (TF-IDF)
  • N-gram model
  • Topic Modeling
How expert explains Natural Language Processing -> stemming
Stemming
How expert explains Natural Language Processing -> N gram model
N-gram model
How expert explains Natural Language Processing Bag of words
Bags of words
How expert explains Natural Language Processing Lemmatization
Lemmatization and Stemming
How expert explains Natural Language Processing ->Topic Modeling
Topic Modeling
  • Vectorization or embedding
  • Using the word embedding technique word2vec, researchers at Google are able to quantify word relationships in an algebraic model
  • The distance between two words in a vector space measure some type of similarity between them.
How expert explains Natural Language Processing -> NLP model
NLP Model
What is the Best NLP Approach
  • Symbolic or statical or Hybrid
  • Symbolic Approach – Handcrafted rules ( Dominant in the first age of NLP)
  • Statistical Approach – Popular after the 2000s with very good results.
Some NLP Applications
  • Information Extraction
  • Question Answering
  • Text Summarization
  • Machine Translation

Hence NLP is an important and difficult approach in machine learning. But proper guidelines of expert you can easily learn such a vast topic of linguistic and computation theory. We discussed How expert explains Natural Language Processing in this article.

Thank You Bal Krishna Bal for your wonderful guideline about NLP.

One thought on “How expert explains Natural Language Processing!

Leave a Reply

Your email address will not be published. Required fields are marked *