# Learning Constraints for Structured Prediction Using Rectifier Networks

arXiv: https://arxiv.org/abs/2006.01209 · HTML: https://mlsanity.com/paper/2006.01209/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 May 2020.

## Built on by (most cited first, 3 of 3)

- [Learning Constraints and Descriptive Segmentation for Subevent Detection](https://mlsanity.com/paper/2109.06316/) (2021)
- [A Solver-Free Framework for Scalable Learning in Neural ILP Architectures](https://mlsanity.com/paper/2210.09082/) (2022)
- [On Regularization and Inference with Label Constraints](https://mlsanity.com/paper/2307.03886/) (2023)

## Abstract (arXiv)

Various natural language processing tasks are structured prediction problems where outputs are constructed with multiple interdependent decisions. Past work has shown that domain knowledge, framed as constraints over the output space, can help improve predictive accuracy. However, designing good constraints often relies on domain expertise. In this paper, we study the problem of learning such constraints. We frame the problem as that of training a two-layer rectifier network to identify valid structures or substructures, and show a construction for converting a trained network into a system of linear constraints over the inference variables. Our experiments on several NLP tasks show that the learned constraints can improve the prediction accuracy, especially when the number of training examples is small.