SyntaxNet Models for the CoNLL 2017 Shared Task
arXiv:1703.04929
Abstract
We describe a baseline dependency parsing system for the CoNLL2017 Shared Task. This system, which we call "ParseySaurus," uses the DRAGNN framework [Kong et al, 2017] to combine transition-based recurrent parsing and tagging with character-based word representations. On the v1.3 Universal Dependencies Treebanks, the new system outpeforms the publicly available, state-of-the-art "Parsey's Cousins" models by 3.47% absolute Labeled Accuracy Score (LAS) across 52 treebanks.
Tech report
References in corpus (7)
- Exploring the Limits of Language Modeling
- Transition-Based Dependency Parsing with Stack Long Short-Term Memory
- Hierarchical Multiscale Recurrent Neural Networks
- Character-based Neural Machine Translation
- Improved Transition-Based Parsing by Modeling Characters instead of Words with LSTMs
- DRAGNN: A Transition-based Framework for Dynamically Connected Neural Networks
- Multilingual Language Processing From Bytes
Cited by in corpus (7)
- Graph Transformer for Graph-to-Sequence Learning
- Semantic Hypergraphs
- On the relation between dependency distance, crossing dependencies, and parsing. Comment on "Dependency distance: a new perspective on syntactic patterns in natural languages" by Haitao Liu et al
- Read, Tag, and Parse All at Once, or Fully-neural Dependency Parsing
- On Multilingual Training of Neural Dependency Parsers
- Char-RNN for Word Stress Detection in East Slavic Languages
- Syntree2Vec - An algorithm to augment syntactic hierarchy into word embeddings