Learning from Rules Generalizing Labeled Exemplars (Spotlight at ICLR 2020)

This video summarizes our paper "Learning from Rules Generalizing Labeled Exemplars". This paper has been accepted as a spotlight at the International Conference on Learning Representations 2020.

Authors: Abhijeet Awasthi, Sabyasachi Ghosh, Rasna Goyal, Sunita Sarawagi

Abstract: In many applications labeled data is not readily available, and needs to be collected via pain-staking human supervision. We propose a rule-exemplar method for collecting human supervision to combine the efficiency of rules with the quality of instance labels. The supervision is coupled such that it is both natural for humans and synergistic for learning. We propose a training algorithm that jointly denoises rules via latent coverage variables, and trains the model through a soft implication loss over the coverage and label variables. The denoised rules and trained model are used jointly for inference. Empirical evaluation on five different tasks shows that (1) our algorithm is more accurate than several existing methods of learning from a mix of clean and noisy supervision, and (2) the coupled rule-exemplar supervision is effective in denoising rules.

Paper: https://openreview.net/forum?id=SkeuexBtDr

Code and datasets: https://github.com/awasthiabhijeet/Learning-From-Rules

Contact: awasthi@cse.iitb.ac.in ( Twitter: https://twitter.com/Awasthi_A_ )