Description:

There has been growing interest on shedding boring and cumbersome “search and get thousand results” interface to move towards a “conversational” interface to ease the reception of deluge of information in various web and mobile applications. While a naive search bar that simplified information extraction and delivery of web pages was the rage in early 2000s, exponential increase in data and information on the Internet is making it natural for the search bar to evolve into a smarter and responsive interface. Not only can this search bar be more responsive in terms of guiding users in an iterative aka conversation based search, but it can also be assistive in fetching information that suits the interests of different users. Sooner or later, such conversational interface will replace the old-generation search bar.

However, building such conversational interface has several technology challenges: a) the interface has to understand and extract intent from natural human inputs in terms of text or speech (this is partly done by the current generation search interfaces), b) it has to generate meaningful dialogue responses to engage users into a conversation, c) it has to understand and use context to assist users in fetching the most relevant information, and while doing so d) make the information results personalized to the user as she uses the interface over time.

How do we solve these technology challenges? Is the ‘conversational search’ a hype or soon to be reality? How are recent advances in deep learning playing their role towards building such ‘chat bots’? How can we build a real interactive search interface using existing web (or Django) and machine learning frameworks. In this talk, I will take a deep dive to answer these questions and present the state of the art in building conversational agents during Django and Tensorflow (and Python, of course!). Tensorflow is a machine/deep learning package (using Python) open sourced by Google and has several advanced features to parse user text queries and personalize search results.

Specifically, I will talk about building Django-based rest frameworks without and with websockets to enable interactive text search interfaces. Such interfaces are expected to become pervasive in coming years to replace web search bar, e-commerce search bars or any domain specific search engines such as education, healthcare etc. I will talk about implementation details of API using Django to enable such interface. The talk will also give an overview of the current state of deep learning techniques to build a chat bot, and provide details a few techniques such as LSTM or sequence to sequence learning in building a chat bot in reality.

Prerequisites:

Django 1.9 TensorFlow 0.9 Python 3.4 Rest frameworks Websockets Django channels Some familiarity wit Machine Learning or Deep Learning

Content URLs:

Link to the presentation: https://www.dropbox.com/s/1egi7ccwk1bu5de/chat-bots-pycon.pdf?dl=0

Speaker Info:

Vijay Gabale is co-founder and CTO of Infilect, an AI-powered Commerce Platform. Infilect has been building a fashion commerce platform to provide exceptional shopping experiences to the Internet consumers. The company has made several innovations in deep learning to process rich multi-media data (text, image, videos) to improve discovery, search and personalization experiences of online consumers.

Prior to co-founding Infilect, he was a research scientist with IBM Research Labs. He graduated with a PhD from IIT Bombay, India in 2012. He has several top tier research publications and software patents to his name. He is also co-organizer of ‘Deep Learning Bangalore’ meetup. He has been actively working in deep learning for past several years and has give several talks in and outside India on the research and applications of deep learning in e-commerce.

Speaker Links:

https://medium.com/@infilect https://www.linkedin.com/in/vijaygabale Recent talks: Deep Learning, Fifth Elephant: https://hasgeek.tv/fifthelephant/deep-learning-conf-2016/1217-vijay-gabale-deep-dive-into-building-chat-bots-using-deep-learning ACM IKDD 2016: Experience Driven Commerce Using Deep Learning http://ikdd.acm.org/Site/CoDS2016/schedule.html (Attendance 100+) IEEE COMSNETS 2016: Matching Fashion Blogs to Fashion Commerce http://www.comsnets.org/archive/2016/waci_workshop.html (Attendance 80+) IBM Research, I-CARE 2015: Contextual Product Discovery in The Wild https://university-relations.in/wps/portal/icare2013 (Attendance 60+)