A Higher-Order Semantic Dependency Parser
Not on the map. Why?
Abstract (arXiv)
Higher-order features bring significant accuracy gains in semantic dependency parsing. However, modeling higher-order features with exact inference is NP-hard. Graph neural networks (GNNs) have been demonstrated to be an effective tool for solving NP-hard problems with approximate inference in many graph learning tasks. Inspired by the success of GNNs, we investigate building a higher-order semantic dependency parser by applying GNNs. Instead of explicitly extracting higher-order features from intermediate parsing graphs, GNNs aggregate higher-order information concisely by stacking multiple GNN layers. Experimental results show that our model outperforms the previous state-of-the-art parser on the SemEval 2015 Task 18 English datasets.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 12 of its 28 references that are in the map. First posted on arXiv 27 Jan 2022.
Builds on
12 of 28 references.
References · 12
- 2017Graph Attention Networkscited by 8,854
- 2018Learning to Solve NP-Complete Problems - A Graph Neural Network for Decision TSPcited by 58
- 2020Efficient Second-Order TreeCRF for Neural Dependency Parsingcited by 48
- 2018Simpler but More Accurate Semantic Dependency Parsingcited by 46
- 2020Distributed Scheduling using Graph Neural Networkscited by 27
- 2019Second-Order Semantic Dependency Parsing with End-to-End Neural Networkscited by 21
- 2019Establishing Strong Baselines for the New Decade: Sequence Tagging, Syntactic and Semantic Parsing with BERTcited by 19
- 2020Transition-based Semantic Dependency Parsing with Pointer Networkscited by 16
- 2019Compositional Semantic Parsing Across Graphbankscited by 15
- 2017Deep Multitask Learning for Semantic Dependency Parsingcited by 10
- 2020Fast semantic parsing with well-typedness guaranteescited by 10
- 2019Multi-Task Semantic Dependency Parsing with Policy Gradient for Learning Easy-First Strategiescited by 9
Built on by
Not cited yet.