Learning from Natural Language Supervision

January 28, 2019
3:00 PM
Halligan 102
Speaker: Shashank Srivastava, Carnegie Mellon University
Host: Matthias Scheutz

Abstract

Humans can efficiently learn and communicate new knowledge about the world through natural language (e.g, the concept of important emails may be described through explanations like ‘late night emails from my advisor are definitely important’). Can machines be similarly taught new tasks and behavior through natural language interactions with their users? In this talk, we'll explore three approaches towards enabling language-based learning in context of classifications tasks. In the first part of the talk, we'll consider how language can be leveraged for interactive feature space construction for machine learning tasks. I'll present a method for jointly (1) learning to interpret open-ended natural language explanations, and (2) learning the classification models, by using explanations in conjunction with a small number of labeled examples of the concept. Secondly, we'll examine an approach for using language as a substitute for labeled data for generalization of machine learning models, which leverages the semantics of quantifiers in everyday language (`definitely', `sometimes', etc.) to enable machine learning with limited or no labeled data. Finally, we'll briefly explore how conversational agents can accelerate the learning process through student-teacher dialog.

Bio

Shashank Srivastava recently received his PhD from the Machine Learning department at CMU, and currently works at Microsoft Research. Shashank's research interests lie in conversational learning and natural language understanding, and his dissertation focuses on helping machines learn from human interactions. Shashank has an undergraduate degree in Computer Science from IIT Kanpur, and a Master’s degree in Language Technologies from CMU. He received the Yahoo InMind Fellowship in 2016-17, and his research has been covered by popular media outlets including GeekWire and New Scientist.