# Graph Convolutions over Constituent Trees for Syntax-Aware Semantic Role Labeling

arXiv: https://arxiv.org/abs/1909.09814 · HTML: https://mlsanity.com/paper/1909.09814/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Sep 2019.

## Built on by (most cited first, 12 of 12)

- [LasUIE: Unifying Information Extraction with Latent Adaptive Structure-aware Generative Language Model](https://mlsanity.com/paper/2304.06248/) (2023)
- [A Double-Graph Based Framework for Frame Semantic Parsing](https://mlsanity.com/paper/2206.09158/) (2022)
- [A Graph-Based Neural Model for End-to-End Frame Semantic Parsing](https://mlsanity.com/paper/2109.12319/) (2021)
- [Transformers as Graph-to-Graph Models](https://mlsanity.com/paper/2310.17936/) (2023)
- [CSynGEC: Incorporating Constituent-based Syntax for Grammatical Error Correction with a Tailored GEC-Oriented Parser](https://mlsanity.com/paper/2211.08158/) (2022)
- [Semantic Role Labeling Meets Definition Modeling: Using Natural Language to Describe Predicate-Argument Structures](https://mlsanity.com/paper/2212.01094/) (2022)
- [An MRC Framework for Semantic Role Labeling](https://mlsanity.com/paper/2109.06660/) (2021)
- [Knowledge-augmented Frame Semantic Parsing with Hybrid Prompt-tuning](https://mlsanity.com/paper/2303.14375/) (2023)
- [MuLMS: A Multi-Layer Annotated Text Corpus for Information Extraction in the Materials Science Domain](https://mlsanity.com/paper/2310.15569/) (2023)
- [Incorporating Constituent Syntax for Coreference Resolution](https://mlsanity.com/paper/2202.10710/) (2022)
- [Text Representation Enrichment Utilizing Graph based Approaches: Stock Market Technical Analysis Case Study](https://mlsanity.com/paper/2211.16103/) (2022)
- [Extensible Multi-Granularity Fusion Network and Transferable Curriculum Learning for Aspect-based Sentiment Analysis](https://mlsanity.com/paper/2402.07787/) (2024)

## Abstract (arXiv)

Semantic role labeling (SRL) is the task of identifying predicates and labeling argument spans with semantic roles. Even though most semantic-role formalisms are built upon constituent syntax and only syntactic constituents can be labeled as arguments (e.g., FrameNet and PropBank), all the recent work on syntax-aware SRL relies on dependency representations of syntax. In contrast, we show how graph convolutional networks (GCNs) can be used to encode constituent structures and inform an SRL system. Nodes in our SpanGCN correspond to constituents. The computation is done in 3 stages. First, initial node representations are produced by `composing' word representations of the first and the last word in the constituent. Second, graph convolutions relying on the constituent tree are performed, yielding syntactically-informed constituent representations. Finally, the constituent representations are `decomposed' back into word representations which in turn are used as input to the SRL classifier. We evaluate SpanGCN against alternatives, including a model using GCNs over dependency trees, and show its effectiveness on standard CoNLL-2005, CoNLL-2012, and FrameNet benchmarks.