Our Favorite Posts Of Last Week (Dec 30, 2018)

Understand Text Summarization and create your own summarizer in python

We all interact with applications which uses text summarization. Many of those applications are for the platform which publishes articles on daily news, entertainment, sports.
Link: https://towardsdatascience.com/understand-text-summarization-and-create-your-own-summarizer-in-python-b26a9f09fc70
Word Count: 1533

Improving HTML Time to First Byte

The Time to First Byte (TTFB) of a site is the time from when the user starts navigating until the HTML for the page they requested starts to arrive. A slow TTFB has been the bane of my existence for more than the ten years I have been running WebPageTest.
Link: https://blog.cloudflare.com/improving-html-time-to-first-byte/
Word Count: 1648

BERT: State of the Art Natural Language Processing (NLP) Model, Explained

BERT (Bidirectional Encoder Representations from Transformers) is a recent paper published by researchers at Google AI Language. It has caused a stir in the Machine Learning community by presenting state-of-the-art results in a wide variety of Natural Language Processing (NLP) tasks, including Question Answering (SQuAD v1.
Link: https://www.kdnuggets.com/2018/12/bert-sota-Natural Language Processing (NLP)-model-explained.html
Word Count: 1606

#SEOisAEO Podcast with Jason Barnard

Following the amazing reception we got for the epic webinar series on SEMrush, #SEOisAEO is continuing into 2019 – as a podcast. The ambiance of the conference setting plus the one-on-one format should give the podcast an extra bit of ‘soul’. Each interview will be released as a podcast.
Link: https://jasonbarnard.com/seoisaeo-podcast/
Word Count: 137

Text Classification with State of the Art Natural Language Processing (NLP) Library — Flair

Why is this big news for Natural Language Processing (NLP)? Flair delivers state-of-the-art performance in solving Natural Language Processing (NLP) problems such as named entity recognition (NER), part-of-speech tagging (PoS), sense disambiguation and text classification. It’s an Natural Language Processing (NLP) framework built on top of PyTorch.
Link: https://towardsdatascience.com/text-classification-with-state-of-the-art-Natural Language Processing (NLP)-library-flair-b541d7add21f
Word Count: 1433


The goal of this project was to learn a model that could generate semantically accurate plot synopses from movie plot summaries. Four seq2seq models were trained and their performance was evaluating by comparing the similarity between words in the target sentences and generated sentences.
Link: https://github.com/jimmychimmyy/TLDRSynopsisGenerator
Word Count: 810

Generative Adversarial Networks – Paper Reading Road Map

This summer, I have worked on Generative Adversarial Networks (GANs) through my research internship. At first, I did not know much about this model, so the very first weeks of my internship included a lot of paper reading.
Link: https://www.kdnuggets.com/2018/10/generative-adversarial-networks-paper-reading-road-map.html
Word Count: 1236

Pivot Billions and Deep Learning enhanced trading models achieve 100% net profit

Deep Learning has revolutionized the fields of image classification, personal assistance, competitive board game play, and many more. However, the financial currency markets have been surprisingly stagnant.
Link: https://www.r-bloggers.com/pivot-billions-and-deep-learning-enhanced-trading-models-achieve-100-net-profit/
Word Count: 375


In this repository, I will show you how to build a neural network from scratch (yes, by using plain python code with no framework involved) that trains by mini-batches using gradient descent. Check nn.py for the code. nn.py is a toy neural network that is meant for educational purposes only.
Link: https://github.com/ahmedbesbes/Neural-Network-from-scratch
Word Count: 246