# Simpler but More Accurate Semantic Dependency Parsing

arXiv: https://arxiv.org/abs/1807.01396 · HTML: https://mlsanity.com/paper/1807.01396/

## Key facts

- Cited by 46 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Jul 2018.

## Built on by (most cited first, 30 of 46)

- [Structured Sentiment Analysis as Dependency Graph Parsing](https://mlsanity.com/paper/2105.14504/) (2021)
- [Pushing the Limits of ChatGPT on NLP Tasks](https://mlsanity.com/paper/2306.09719/) (2023)
- [Improving Text-to-SQL with Schema Dependency Learning](https://mlsanity.com/paper/2103.04399/) (2021)
- [AMR Parsing with Action-Pointer Transformer](https://mlsanity.com/paper/2104.14674/) (2021)
- [Effective Token Graph Modeling using a Novel Labeling Strategy for Structured Sentiment Analysis](https://mlsanity.com/paper/2203.10796/) (2022)
- [Large-Scale Contextualised Language Modelling for Norwegian](https://mlsanity.com/paper/2104.06546/) (2021)
- [FinReport: Explainable Stock Earnings Forecasting via News Factor Analyzing Model](https://mlsanity.com/paper/2403.02647/) (2024)
- [Question Decomposition with Dependency Graphs](https://mlsanity.com/paper/2104.08647/) (2021)
- [Sparse Fuzzy Attention for Structured Sentiment Analysis](https://mlsanity.com/paper/2109.06719/) (2021)
- [Coordinate Constructions in English Enhanced Universal Dependencies: Analysis and Computational Modeling](https://mlsanity.com/paper/2103.08955/) (2021)
- [EventGraph: Event Extraction as Semantic Graph Parsing](https://mlsanity.com/paper/2210.08646/) (2022)
- [Structural generalization in COGS: Supertagging is (almost) all you need](https://mlsanity.com/paper/2310.14124/) (2023)
- [TGIF: Tree-Graph Integrated-Format Parser for Enhanced UD with Two-Stage Generic- to Individual-Language Finetuning](https://mlsanity.com/paper/2107.06907/) (2021)
- [Automated Evaluation for Student Argumentative Writing: A Survey](https://mlsanity.com/paper/2205.04083/) (2022)
- [AutoAM: An End-To-End Neural Model for Automatic and Universal Argument Mining](https://mlsanity.com/paper/2309.09300/) (2023)
- [Enhanced Universal Dependency Parsing with Automated Concatenation of Embeddings](https://mlsanity.com/paper/2107.02416/) (2021)
- [COMBO: State-of-the-Art Morphosyntactic Analysis](https://mlsanity.com/paper/2109.05361/) (2021)
- [Direct parsing to sentiment graphs](https://mlsanity.com/paper/2203.13209/) (2022)
- [On graph-based reentrancy-free semantic parsing](https://mlsanity.com/paper/2302.07679/) (2023)
- [JSEEGraph: Joint Structured Event Extraction as Graph Parsing](https://mlsanity.com/paper/2306.14633/) (2023)
- [Predicting Music Hierarchies with a Graph-Based Neural Decoder](https://mlsanity.com/paper/2306.16955/) (2023)
- [Scope-enhanced Compositional Semantic Parsing for DRT](https://mlsanity.com/paper/2407.01899/) (2024)
- [Dependency Graph Parsing as Sequence Labeling](https://mlsanity.com/paper/2410.17972/) (2024)
- [The DCU-EPFL Enhanced Dependency Parser at the IWPT 2021 Shared Task](https://mlsanity.com/paper/2107.01982/) (2021)
- [Fast and Accurate End-to-End Span-based Semantic Role Labeling as Word-based Graph Parsing](https://mlsanity.com/paper/2112.02970/) (2021)
- [Modeling Label Correlations for Second-Order Semantic Dependency Parsing with Mean-Field Inference](https://mlsanity.com/paper/2204.03619/) (2022)
- [Structured Sentiment Analysis as Transition-based Dependency Graph Parsing](https://mlsanity.com/paper/2305.05311/) (2023)
- [MuLMS: A Multi-Layer Annotated Text Corpus for Information Extraction in the Materials Science Domain](https://mlsanity.com/paper/2310.15569/) (2023)
- [LyS at SemEval-2024 Task 3: An Early Prototype for End-to-End Multimodal Emotion Linking as Graph-Based Parsing](https://mlsanity.com/paper/2405.06483/) (2024)
- [End-to-End Argument Mining through Autoregressive Argumentative Structure Prediction](https://mlsanity.com/paper/2510.16363/) (2025)

## Abstract (arXiv)

While syntactic dependency annotations concentrate on the surface or functional structure of a sentence, semantic dependency annotations aim to capture between-word relationships that are more closely related to the meaning of a sentence, using graph-structured representations. We extend the LSTM-based syntactic parser of Dozat and Manning (2017) to train on and generate these graph structures. The resulting system on its own achieves state-of-the-art performance, beating the previous, substantially more complex state-of-the-art system by 0.6% labeled F1. Adding linguistically richer input representations pushes the margin even higher, allowing us to beat it by 1.9% labeled F1.