Question answering is a very popular task in Natural language processing but question generation is novel and hasn’t been explored much yet.
Question generation has a lot of use cases with the most prominent one being the ability to generate quick assessments from any given content. It would help school teachers in generating worksheets from any given chapter quickly and decrease their work burden during Covid-19.
I along with two other awesome interns Parth Chokhra and Vaibhav Tiwari built an easy-to-use, open-source library to advance the research in question generation using the state-of-the-art T5 transformer model from Hugging Face library.
You might have seen the traditional word2vec or Glove word embeddings examples that show King -Man+Woman = Queen. Here Queen will be returned from the word embedding algorithm given the words King, Man, and Woman. Today we will see how we can use this structure to solve a real-world problem.
Distractors are the wrong answers in a multiple-choice question.
For example, if a given multiple choice question has the game Cricket as the correct answer then we need to generate wrong choices (distractors) like Football, Golf, Ultimate Frisbee, etc.
I’m sure most of you have heard about OpenAI’s GPT-3 and its insane text generation capabilities learning from only a few examples.
The concept of feeding a model with very little training data and making it learn to do a novel task is called Few-shot learning.
A website GPT-3 examples captures all the impressive applications of GPT-3 that the community has come up with, since its release. GPT-3 is shown to generate the whole Frontend code from just a text description of how a website looks like. It is shown to generate a complete marketing copy from just a small…
Imagine that you are a writer and you are searching for the best image that goes with your blog or book. You have a search phrase in mind like “Tiger playing in the snow”. You go onto copyright-free image websites like Pixabay or Unsplash and try out various combinations of keywords like “Tiger”, “Snow”, “Tiger Snow” etc to find relevant images.
If you are lucky you find the exact image that you are looking for on the first page or in the top N retrieved results.
Since the images in these websites have only tags, you are limited by the…
It has been almost three years since I had quit my job in silicon valley, moved back home (India), and took a plunge into entrepreneurship.
The journey accompanied with its ups and downs had spawned a myriad of emotions and thoughts. Sometimes they transformed into what I can call motivational quotes.
Quite often I see my friends ardently following popular gurus/influencers on social media like Naval Ravikant, Simon Sinek, Sadhguru, Yuval Noah, etc.
From time to time, I get to watch/hear the content from these and other influencers in one way or the other. Sure they have great things to say, but surprisingly enough I never felt there was a significant delta in the upgrade of my personal wisdom.
If I have to be honest, most things that the world calls as wisdom appeared to me as just common sense packaged well.
Observe — The one word that helped me navigate…
A few years back when I was building my career as a software developer, I was constantly faced with the question of what should I focus on?
Should I learn blockchain, AR/VR tech, mobile app development, Core machine learning, Cyber Security, self-driving car technology, or something completely new?
The answers I was looking for were found in the most unlikely places — Entrepreneurship, Product management, and Moocs (Online courses).
Hence I suggest you become a developerpreneur to figure out the answers for yourself. By developerpreneur, I mean a developer with an entrepreneur mindset.