CSE Colloquium: Human-Centric Natural Language Processing

Zoom Information 

Join from PC, Mac, Linux, iOS or Android: https://psu.zoom.us/j/847532818 

or iPhone one-tap (US Toll): +13126266799,847532818# or +16468769923,847532818# 

or Telephone: 

Dial: 

+1 312 626 6799 (US Toll) 

+1 646 876 9923 (US Toll) 

+1 346 248 7799 (US Toll) 

+1 669 900 6833 (US Toll) 

+1 253 215 8782 (US Toll) 

+1 301 715 8592 (US Toll) 

Meeting ID: 847 532 818 

International numbers available: https://psu.zoom.us/u/abShu8Brox 

Abstract: Despite remarkable progress, modern natural language processing (NLP) systems are brittle and biased because of a fundamental limitation -- they ignore the human and social context that language is grounded in and are insensitive to differences in language use across contexts like time, geography and domains. To address this limitation, I advocate for NLP that is human-centric and robust to language variation. First, I will demonstrate that one can model human context by learning a small set of latent human factors (traits) from their background language. I will show that these traits broadly capture meaningful differences among people, are generally predictive of a variety of outcomes and improve the performance of NLP models on tasks such as stance and sarcasm detection. In the second part of the talk, I will propose methods to learn socially grounded word embeddings that reliably model semantic variation across contexts and briefly outline their effectiveness on downstream tasks. Finally, I conclude by mapping out open problems and challenges that naturally guide future research towards the larger goal of robust, human-centric and fair natural language processing. 

Biography: Vivek Kulkarni is a Postdoctoral Research Scholar at Stanford in the Stanford NLP group advised by Prof. Dan Jurafsky. His research broadly focuses on making NLP robust to language variation and human-centric. He received his Ph.D. in Computer Science from Stony Brook University in 2017. His work has been featured in MIT Tech Review, the VICE and, The Guardian.