# Structured Tuning for Semantic Role Labeling

arXiv: https://arxiv.org/abs/2005.00496 · HTML: https://mlsanity.com/paper/2005.00496/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 May 2020.

## Built on by (most cited first, 10 of 10)

- [Semantic Role Labeling as Dependency Parsing: Exploring Latent Tree Structures Inside Arguments](https://mlsanity.com/paper/2110.06865/) (2021)
- [Is My Model Using The Right Evidence? Systematic Probes for Examining Evidence-Based Tabular Reasoning](https://mlsanity.com/paper/2108.00578/) (2021)
- [Learning Constraints and Descriptive Segmentation for Subevent Detection](https://mlsanity.com/paper/2109.06316/) (2021)
- [Evaluating Relaxations of Logic for Neural Networks: A Comprehensive Study](https://mlsanity.com/paper/2107.13646/) (2021)
- [An MRC Framework for Semantic Role Labeling](https://mlsanity.com/paper/2109.06660/) (2021)
- [Improving Portuguese Semantic Role Labeling with Transformers and Transfer Learning](https://mlsanity.com/paper/2101.01213/) (2021)
- [Contextualized Semantic Distance between Highly Overlapped Texts](https://mlsanity.com/paper/2110.01176/) (2021)
- [The Integer Linear Programming Inference Cookbook](https://mlsanity.com/paper/2307.00171/) (2023)
- [Learning Semantic Role Labeling from Compatible Label Sequences](https://mlsanity.com/paper/2305.14600/) (2023)
- [An Analysis under a Unified Fomulation of Learning Algorithms with Output Constraints](https://mlsanity.com/paper/2406.01647/) (2024)

## Abstract (arXiv)

Recent neural network-driven semantic role labeling (SRL) systems have shown impressive improvements in F1 scores. These improvements are due to expressive input representations, which, at least at the surface, are orthogonal to knowledge-rich constrained decoding mechanisms that helped linear SRL models. Introducing the benefits of structure to inform neural models presents a methodological challenge. In this paper, we present a structured tuning framework to improve models using softened constraints only at training time. Our framework leverages the expressiveness of neural networks and provides supervision with structured loss components. We start with a strong baseline (RoBERTa) to validate the impact of our approach, and show that our framework outperforms the baseline by learning to comply with declarative constraints. Additionally, our experiments with smaller training sizes show that we can achieve consistent improvements under low-resource scenarios.