paper-with-me

Papers

Effective Online Reordering with Arc-Eager Transitions

2017-09-01 · WS 2017 9 · Ryosuke Kohita, Hiroshi Noji, Yuji Matsumoto

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.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

ARCDependency ParsingTransition-Based Dependency Parsing

Similar Papers 제목 키워드 기반

EagerPy: Writing Code That Works Natively with PyTorch, TensorFlow, JAX, and NumPy

2020-08-10 · Jonas Rauber, Matthias Bethge, Wieland Brendel

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

2021-03-26 · Chihiro Watanabe, Taiji Suzuki

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 Prediction

An Eager Splitting Strategy for Online Decision Trees

2020-10-20 · Chaitanya Manapragada, Heitor M Gomes, Mahsa Salehi, Albert Bifet 외

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

2021-04-01 · Zixuan Jiang, Jiaqi Gu, Mingjie Liu, Keren Zhu 외

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

2024-11-01 · Ruisi Zhang, Tianyu Liu, Will Feng, Andrew Gu 외

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-…