NLP Masterclass | Modeling Fallacies in NLP

July 4, 2020

NLP Masterclass | Modelling Fallacies in NLP

Talk 1 :

About author
Pratik is a remote working NLP engineer from IIT Bombay who loves discussing text problems. He enjoys participating in hackathons and writing on his medium publication. You can find more about him at pratik.ai

Title: Anti-patterns in NLP

Abstract: NLP has progressed many folds in the last 3 years. Unfortunately, we have not written or discussed much around how to solve problems in simplest ways. Businesses love to talk about BERT to look cool while engineers pride themselves on trying SOTA models. In this talk, I will discuss common anti-patterns which happen in the industry while solving text problems

Current state of modelling
Types of AI idiots in NLP
Model selection logic

[MASTERCLASS] NLP

Code Focussed Session

Introduction to the basics of NLP

what is nlp ?
how it is used in real life examples?
word
tokenization - word and sentence
minimum edit distance
max match algorithm
regular expressions
pos tags
lemmatization
stemming
false positive and false negative
removing stop words and punctuation why important
zif's law
n - gram language model
word embedding
tf-idf
bag of words

Speaker : Manpreet Budhraja

Linkedin - https://www.linkedin.com/in/manpreet-budhraja/