Learn Python
Learn Data Structure & Algorithm
Learn Numpy
Learn Pandas
Learn Matplotlib
Learn Seaborn
Learn Statistics
Learn Math
Learn MATLAB
Learn Machine learning
Learn Github
Learn OpenCV
Introduction
Setup
ANN
Working process ANN
Propagation
Bias parameter
Activation function
Loss function
Overfitting and Underfitting
Optimization function
Chain rule
Minima
Gradient problem
Weight initialization
Dropout
ANN Regression Exercise
ANN Classification Exercise
Hyper parameter tuning
CNN
CNN basics
Convolution
Padding
Pooling
Data argumentation
Flattening
Create Custom Dataset
Binary Classification Exercise
Multiclass Classification Exercise
Transfer learning
Transfer model Basic template
RNN
How RNN works
LSTM
Bidirectional RNN
Sequence to sequence
Attention model
Transformer model
Bag of words
Tokenization & Stop words
Stemming & Lemmatization
TF-IDF
N-Gram
Word embedding
Normalization
Pos tagging
Parser
semantic analysis
Regular expression
Learn MySQL
Learn MongoDB
Learn Web scraping
Learn Excel
Learn Power BI
Learn Tableau
Learn Docker
Learn Hadoop
Pos tagging stands for parts of speech tagging. Suppose we have a sentence and in the sentence, we will have
lots of words. What we do here is that, we will assign a pos tag for each word.
Let's see an example:
We have a sentence: Rafsun ate a pizza.
Now if we write parts of speech of these words then we will get:
Rafsun=Noun
ate=Verb
a=Determiner
pizza=Noun
So the tag will be for these words:
Rafsun=Noun=NN
ate=Verb=VB
a=Determiner=DT
pizza=Noun=NN
So assigning a tag like these for each word is called pos tagging. These are lots of tags:
Pos tagging is the process of converting a sentence into forms. Here forms means list of words, from a list of
tuples which are word, pos tag.
We have three types of techniques to perform pos tagging:
1. Rule-base tagging:
Here we pass input and dictionary and after the process, it will return word and pos and some words will get
two pos but we need one because, in a sentence, a word can only have one part of speech. To get one pos we use
the rule.
Let's see an example:
We have a sentence: I want to read a book
Here book can be a noun or verb.
To get the correct pos we will write a condition and that is:
if the book is after a determiner then it is a noun otherwise verb. Now in the sentence "book" is after
a determiner so here "book" is a noun. Now we will get one word and one pos as an output. Here we write these
rules by ourselves.
2.Stochastic tagging:
Here we have two methods:
1. Word frequency:
Here we have a big corpus or data. Now if a word comes like pen. Now it will try to find that in the past how
many times which tag comes for the pen. Suppose it gets that most of the times pen has tag noun. So it will
assign noun for pen. So we can say that it will assign the most frequently use tag for a word.
2. Tag sequence:
In this method, the algorithm sees the previous tag. Suppose we have "a pen". Now, this algorithm will see the
previous tag. Here the previous word of "book" is "a" and "a" is a determiner and we know that after
determiner noun comes. So it will assign noun tag for "book".
3. Transformation based tagging:
It is a combination of rule-based and stochastic tagging. Here we apply rules (as like rule base tagging) and
also have big corpus or data(as like stochastic tagging ). At first, it will assign a common tag with all the
words. After this, it tries to find where it can do changes. So it will apply the rule and will do the changes
where needed. It will apply the rule again and again until there is no changes left.