Incidental Supervision: Moving beyond Supervised Learning
This addresses the supervision bottleneck for researchers and practitioners in ML and NLP, but appears incremental as it builds on existing paradigms.
The paper tackles the problem of costly and non-scalable supervision signals in machine learning by proposing learning paradigms to alleviate this bottleneck, demonstrating their benefits in inducing semantic representations from text.
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.