Natural Language Processing for Deep Learning
Machine learning is everywhere in today's NLP, but by and large machine learning amounts to numerical optimization of weights for human designed representations and features. The goal of deep learning is to explore how computers can take advantage of data to develop features and representations appropriate for complex interpretation tasks. I’ll be speaking on basic motivation, ideas, models and learning algorithms in deep learning for natural language processing. I’ll be talking about models which perform very well on various NLP tasks such as language modeling, POS tagging, named entity recognition, sentiment analysis and paraphrase detection, among others. The most attractive quality of these techniques is that they can perform well without any external hand-designed resources or time-intensive feature engineering. Despite these advantages, many researchers in NLP are not familiar with these methods. The goal of the talk will be to make the inner workings of these techniques transparent, intuitive and their results interpretable, rather than black boxes labeled "magic here". The first part of the talk will involve the basics of neural networks, neural word vectors, several simple models based on local windows and the math and algorithms of training via backpropagation and the second section will involve recursive neural networks which can learn structured tree outputs as well as vector representations for phrases and sentences.The principle goal, again, is to make these methods appear intuitive and interpretable rather than mathematically confusing. By this end of the talk, the audience members should have a clear understanding of how to build a deep learning system for word-, sentence- and document-level tasks.
Passionate about Cognitive Computing, Deep Learning and AI. Expert in R, Python, SAS and mongoDB. Vision is to build a cognitive computer which can replicate the 22 billion neurons and 220 trillion synapses of Human Cortex in a portable system! Founded a startup at age 17. Raised seed funding. Got published in Hindustan Times, Yourstory, VCCircle, Techaloo, Foradian, Inc42, The Campus Entrepreneur and many other publications. Got featured as Top under 19 CEOs by IIM Indore and GTL Ventures, Ranked among Top 9 college startups that turned into big companies by YourStory Media Pvt Ltd. Exited from the startup. Worked as an acting COO of Y-center India at the age of 19 and established Y-center (based out of Philly, USA) in India. Former Cognitive Researcher at Institute of Nuclear Medicine and Allied Sciences -DRDO. Served as a Research Fellow and Assistant at IIM Ahmedabad and IISc Bangalore. Also worked as a Data Science intern at some corporate firms like Red Hat, Inc, Adapty, Inc, YourStory Media Pvt Ltd, Wikimedia Foundation. Currently working at Facebook on various Machine Learning and AI projects in India.