# Semantic Role Labeling with Iterative Structure Refinement

arXiv: https://arxiv.org/abs/1909.03285 · HTML: https://mlsanity.com/paper/1909.03285/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Sep 2019.

## Built on by (most cited first, 5 of 5)

- [One Question Answering Model for Many Languages with Cross-lingual Dense Passage Retrieval](https://mlsanity.com/paper/2107.11976/) (2021)
- [End-to-end Semantic Role Labeling with Neural Transition-based Model](https://mlsanity.com/paper/2101.00394/) (2021)
- [Syntax-Aware Graph-to-Graph Transformer for Semantic Role Labelling](https://mlsanity.com/paper/2104.07704/) (2021)
- [Transition-based Semantic Role Labeling with Pointer Networks](https://mlsanity.com/paper/2205.10023/) (2022)
- [LLMs Can Also Do Well! Breaking Barriers in Semantic Role Labeling via Large Language Models](https://mlsanity.com/paper/2506.05385/) (2025)

## Abstract (arXiv)

Modern state-of-the-art Semantic Role Labeling (SRL) methods rely on expressive sentence encoders (e.g., multi-layer LSTMs) but tend to model only local (if any) interactions between individual argument labeling decisions. This contrasts with earlier work and also with the intuition that the labels of individual arguments are strongly interdependent. We model interactions between argument labeling decisions through it iterative refinement. Starting with an output produced by a factorized model, we iteratively refine it using a refinement network. Instead of modeling arbitrary interactions among roles and words, we encode prior knowledge about the SRL problem by designing a restricted network architecture capturing non-local interactions. This modeling choice prevents overfitting and results in an effective model, outperforming strong factorized baseline models on all 7 CoNLL-2009 languages, and achieving state-of-the-art results on 5 of them, including English.