# Neural-Davidsonian Semantic Proto-role Labeling

arXiv: https://arxiv.org/abs/1804.07976 · HTML: https://mlsanity.com/paper/1804.07976/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Apr 2018.

## Built on by (most cited first, 9 of 9)

- [Holmes: A Benchmark to Assess the Linguistic Competence of Language Models](https://mlsanity.com/paper/2404.18923/) (2024)
- [Automatic Document Selection for Efficient Encoder Pretraining](https://mlsanity.com/paper/2210.10951/) (2022)
- [Pretraining Text Encoders with Adversarial Mixture of Training Signal Generators](https://mlsanity.com/paper/2204.03243/) (2022)
- [Decomposing and Recomposing Event Structure](https://mlsanity.com/paper/2103.10387/) (2021)
- [On Event Individuation for Document-Level Information Extraction](https://mlsanity.com/paper/2212.09702/) (2022)
- [Multi-Task Learning for Joint Semantic Role and Proto-Role Labeling](https://mlsanity.com/paper/2210.07270/) (2022)
- [Examining Political Rhetoric with Epistemic Stance Detection](https://mlsanity.com/paper/2212.14486/) (2022)
- [Implications of Annotation Artifacts in Edge Probing Test Datasets](https://mlsanity.com/paper/2310.13856/) (2023)
- [Do We Really Need GNNs with Explicit Structural Modeling? MLPs Suffice for Language Model Representations](https://mlsanity.com/paper/2506.21682/) (2025)

## Abstract (arXiv)

We present a model for semantic proto-role labeling (SPRL) using an adapted bidirectional LSTM encoding strategy that we call "Neural-Davidsonian": predicate-argument structure is represented as pairs of hidden states corresponding to predicate and argument head tokens of the input sequence. We demonstrate: (1) state-of-the-art results in SPRL, and (2) that our network naturally shares parameters between attributes, allowing for learning new attribute types with limited added supervision.