# Backpropagating through Structured Argmax using a SPIGOT

arXiv: https://arxiv.org/abs/1805.04658 · HTML: https://mlsanity.com/paper/1805.04658/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 May 2018.

## Built on by (most cited first, 11 of 11)

- [On Learning Latent Models with Multi-Instance Weak Supervision](https://mlsanity.com/paper/2306.13796/) (2023)
- [Combinatorial Optimization for Panoptic Segmentation: A Fully Differentiable Approach](https://mlsanity.com/paper/2106.03188/) (2021)
- [Beam Tree Recursive Cells](https://mlsanity.com/paper/2305.19999/) (2023)
- [Recursion in Recursion: Two-Level Nested Recursion for Length Generalization with Scalability](https://mlsanity.com/paper/2311.04449/) (2023)
- [Learning to Look Inside: Augmenting Token-Based Encoders with Character-Level Information](https://mlsanity.com/paper/2108.00391/) (2021)
- [Efficient Beam Tree Recursion](https://mlsanity.com/paper/2307.10779/) (2023)
- [Learning with Latent Structures in Natural Language Processing: A Survey](https://mlsanity.com/paper/2201.00490/) (2022)
- [Symbolic Autoencoding for Self-Supervised Sequence Learning](https://mlsanity.com/paper/2402.10575/) (2024)
- [To be Continuous, or to be Discrete, Those are Bits of Questions](https://mlsanity.com/paper/2406.07812/) (2024)
- [Imbalances in Neurosymbolic Learning: Characterization and Mitigating Strategies](https://mlsanity.com/paper/2407.10000/) (2024)
- [Neuro-symbolic Weak Supervision: Theory and Semantics](https://mlsanity.com/paper/2503.18509/) (2025)

## Abstract (arXiv)

We introduce the structured projection of intermediate gradients optimization technique (SPIGOT), a new method for backpropagating through neural networks that include hard-decision structured predictions (e.g., parsing) in intermediate layers. SPIGOT requires no marginal inference, unlike structured attention networks (Kim et al., 2017) and some reinforcement learning-inspired solutions (Yogatama et al., 2017). Like so-called straight-through estimators (Hinton, 2012), SPIGOT defines gradient-like quantities associated with intermediate nondifferentiable operations, allowing backpropagation before and after them; SPIGOT's proxy aims to ensure that, after a parameter update, the intermediate structure will remain well-formed. We experiment on two structured NLP pipelines: syntactic-then-semantic dependency parsing, and semantic parsing followed by sentiment classification. We show that training with SPIGOT leads to a larger improvement on the downstream task than a modularly-trained pipeline, the straight-through estimator, and structured attention, reaching a new state of the art on semantic dependency parsing.