Incidental Supervision: Moving beyond Supervised Learning

TL;DR

This paper explores alternative learning paradigms that reduce the reliance on costly supervision signals for inducing semantic representations from natural language and visual data.

Contribution

It introduces several novel learning paradigms aimed at overcoming supervision bottlenecks in semantic representation tasks.

Findings

Demonstrates effectiveness of new paradigms in multiple semantic tasks

Reduces supervision requirements for natural language and visual data

Improves scalability of semantic learning models

Abstract

Machine Learning and Inference methods have become ubiquitous in our attempt to induce more abstract representations of natural language text, visual scenes, and other messy, naturally occurring data, and support decisions that depend on it. However, learning models for these tasks is difficult partly because generating the necessary supervision signals for it is costly and does not scale. This paper describes several learning paradigms that are designed to alleviate the supervision bottleneck. It will illustrate their benefit in the context of multiple problems, all pertaining to inducing various levels of semantic representations from text.