paper-with-me

홈 › Papers

Representation Learning and Dynamic Programming for Arc-Hybrid Parsing

2019-11-01 · CONLL 2019 11 · Joseph Le Roux, Antoine Rozenknop, Mathieu Lacroix

We present a new method for transition-based parsing where a solution is a pair made of a dependency tree and a derivation graph describing the construction of the former. From this representation we are able to derive an efficient parsing algorithm and design a neural network that learns vertex representations and arc scores. Experimentally, although we only train via local classifiers, our approach improves over previous arc-hybrid systems and reach state-of-the-art parsing accuracy.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

ARCRepresentation Learning

Similar Papers 제목 키워드 기반

Dependency-based Hybrid Trees for Semantic Parsing

2018-09-01 · EMNLP 2018 10 · Zhanming Jie, Wei Lu

We propose a novel dependency-based hybrid tree model for semantic parsing, which converts natural language utterance into machine interpretable meaning representations. Unlike previous state-of-the-art models, the seman…

Semantic Parsing

Fast(er) Exact Decoding and Global Training for Transition-Based Dependency Parsing via a Minimal Feature Set

2017-08-30 · EMNLP 2017 9 · Tianze Shi, Liang Huang, Lillian Lee

We first present a minimal feature set for transition-based dependency parsing, continuing a recent trend started by Kiperwasser and Goldberg (2016a) and Cross and Huang (2016a) of using bi-directional LSTM features. We …

ARCDependency ParsingTransition-Based Dependency Parsing

Optimal Incremental Parsing via Best-First Dynamic Programming

2013-10-01 · EMNLP 2013 10 · Kai Zhao, James Cross, Liang Huang
Dependency Parsing

Dynamic Programming for Higher Order Parsing of Gap-Minding Trees

2012-07-01 · EMNLP 2012 7 · Emily Pitler, Sampath Kannan, Mitchell Marcus

Linear-Time Constituency Parsing with RNNs and Dynamic Programming

2018-05-17 · ACL 2018 7 · Juneki Hong, Liang Huang

Recently, span-based constituency parsing has achieved competitive accuracies with extremely simple models by using bidirectional RNNs to model "spans". However, the minimal span parser of Stern et al (2017a) which holds…

Boundary DetectionConstituency ParsingDiscourse ParsingSentence