AI Seminar

The Physics Behind Automating Content Authoring

Balaji Vasan SrinivasanSenior Research ScientistAdobe Research Big Data Experience Labs

In the digital era, enterprises are required to continuously engage with their online customers to maintain a brand presence. This requires creation of quality and useful content to customers for engaging and attracting customers towards a brand. However, with the increase in the number of channels and personalization being the key, it is important for content writers to quickly create multiple variants and personalize them towards the needs of their customers. Automating these variant creation can help improve their productivity. In this talk, I will first outline some of the research challenges and opportunities in this broad space. I will then cover some of our recent works in this space for generating a elaborate variants via text expansion and tailored shorter variants via tuned summary generation. In the former problem, I will talk about an ILP formulation for creating an elaborate version of a text based on similar materials in the enterprise repository. In the latter problem, I will touch upon ways to tune summaries to the vocabulary of the audience and their topical interests.
Balaji Vasan Srinivasan is a senior research scientist at the Adobe Research Big data Experience Labs, Bangalore, India. His current research work is around teaching machines to author online content and automating the authoring workflows. His research interests span the spaces of natural language processing, social data analytics and high performance computing. He completed his Ph.D. in Computer science at the University of Maryland in September 2011, M.S. in Electrical engineering from University of Maryland in 2008 and B.E. in Electrical engineering from Anna University (India) in 2006.

Sponsored by

CSE, SoarTech Seminar

Faculty Host

Rada Mihalcea