Effective Online Reordering with Arc-Eager Transitions
We present a new transition system with word reordering for unrestricted non-projective dependency parsing. Our system is based on decomposed arc-eager rather than arc-standard, which allows more flexible ambiguity resolution between a local projective and non-local crossing attachment. In our experiment on Universal Dependencies 2.0, we find our parser outperforms the ordinary swap-based parser particularly on languages with a large amount of non-projectivity.
Code (0)
등록된 구현이 없습니다.
Tasks
ARCDependency ParsingTransition-Based Dependency ParsingSimilar Papers 제목 키워드 기반
EagerPy: Writing Code That Works Natively with PyTorch, TensorFlow, JAX, and NumPy
EagerPy is a Python framework that lets you write code that automatically works natively with PyTorch, TensorFlow, JAX, and NumPy. Library developers no longer need to choose between supporting just one of these framewor…
Deep Two-Way Matrix Reordering for Relational Data Analysis
Matrix reordering is a task to permute the rows and columns of a given observed matrix such that the resulting reordered matrix shows meaningful or interpretable structural patterns. Most existing matrix reordering techn…
Vocal Bursts Valence PredictionAn Eager Splitting Strategy for Online Decision Trees
Decision tree ensembles are widely used in practice. In this work, we study in ensemble settings the effectiveness of replacing the split strategy for the state-of-the-art online tree learner, Hoeffding Tree, with a rigo…
Optimizer Fusion: Efficient Training with Better Locality and Parallelism
Machine learning frameworks adopt iterative optimizers to train neural networks. Conventional eager execution separates the updating of trainable parameters from forward and backward computations. However, this approach …
SimpleFSDP: Simpler Fully Sharded Data Parallel with torch.compile
Distributed training of large models consumes enormous computation resources and requires substantial engineering efforts to compose various training techniques. This paper presents SimpleFSDP, a PyTorch-native compiler-…