An Empirical Investigation of Structured Output Modeling for Graph-based Neural Dependency Parsing
In this paper, we investigate the aspect of structured output modeling for the state-of-the-art graph-based neural dependency parser (Dozat and Manning, 2017). With evaluations on 14 treebanks, we empirically show that global output-structured models can generally obtain better performance, especially on the metric of sentence-level Complete Match. However, probably because neural models already learn good global views of the inputs, the improvement brought by structured output modeling is modest.
Code (1)
Tasks
Dependency ParsingSentenceSimilar Papers 제목 키워드 기반
Graph Conditional Variational Models: Too Complex for Multiagent Trajectories?
Recent advances in modeling multiagent trajectories combine graph architectures such as graph neural networks (GNNs) with conditional variational models (CVMs) such as variational RNNs (VRNNs). Originally, CVMs have been…
Graph Mixture Density Networks
We introduce the Graph Mixture Density Networks, a new family of machine learning models that can fit multimodal output distributions conditioned on graphs of arbitrary topology. By combining ideas from mixture models an…
Density EstimationGraph Representation LearningRepresentation LearningNon-parametric Structured Output Networks
Deep neural networks (DNNs) and probabilistic graphical models (PGMs) are the two main tools for statistical modeling. While DNNs provide the ability to model rich and complex relationships between input and output varia…
Graphy'our Data: Towards End-to-End Modeling, Exploring and Generating Report from Raw Data
Large Language Models (LLMs) have recently demonstrated remarkable performance in tasks such as Retrieval-Augmented Generation (RAG) and autonomous AI agent workflows. Yet, when faced with large sets of unstructured docu…
AI AgentRAGRetrieval-augmented GenerationSurvey