TASK	DATASET	MODEL	METRIC NAME	METRIC VALUE	GLOBAL RANK
Chinese Dependency Parsing	Chinese Pennbank	Ballesteros et al. (2016)	LAS	86.21	# 2
Chinese Dependency Parsing	Chinese Pennbank	Ballesteros et al. (2016)	UAS	87.65	# 3
Dependency Parsing	Penn Treebank	Arc-hybrid	POS	97.3	# 5
Dependency Parsing	Penn Treebank	Arc-hybrid	UAS	93.56	# 21
Dependency Parsing	Penn Treebank	Arc-hybrid	LAS	91.42	# 21

Badge	Markdown
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/training-with-exploration-improves-a-greedy/chinese-dependency-parsing-on-chinese)](https://paperswithcode.com/sota/chinese-dependency-parsing-on-chinese?p=training-with-exploration-improves-a-greedy)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/training-with-exploration-improves-a-greedy/dependency-parsing-on-penn-treebank)](https://paperswithcode.com/sota/dependency-parsing-on-penn-treebank?p=training-with-exploration-improves-a-greedy)`

Training with Exploration Improves a Greedy Stack-LSTM Parser

11 Mar 2016 · Miguel Ballesteros, Yoav Goldberg, Chris Dyer, Noah A. Smith ·

We adapt the greedy Stack-LSTM dependency parser of Dyer et al. (2015) to support a training-with-exploration procedure using dynamic oracles(Goldberg and Nivre, 2013) instead of cross-entropy minimization. This form of training, which accounts for model predictions at training time rather than assuming an error-free action history, improves parsing accuracies for both English and Chinese, obtaining very strong results for both languages. We discuss some modifications needed in order to get training with exploration to work well for a probabilistic neural-network.

PDF Abstract

Code

Add Remove Mark official

No code implementations yet. Submit your code now

Tasks

Add Remove

Chinese Dependency Parsing

Dependency Parsing

Datasets

Penn Treebank

Results from the Paper

Edit

Ranked #2 on Chinese Dependency Parsing on Chinese Pennbank

Get a GitHub badge

Task	Dataset	Model	Metric Name	Metric Value	Global Rank	Benchmark
Chinese Dependency Parsing	Chinese Pennbank	Ballesteros et al. (2016)	LAS	86.21	# 2	Compare
Chinese Dependency Parsing	Chinese Pennbank	Ballesteros et al. (2016)	UAS	87.65	# 3	Compare
Dependency Parsing	Penn Treebank	Arc-hybrid	POS	97.3	# 5	Compare
			UAS	93.56	# 21	Compare
			LAS	91.42	# 21	Compare

Methods

Add Remove

No methods listed for this paper. Add relevant methods here

Edit Social Preview

Training with Exploration Improves a Greedy Stack-LSTM Parser

Code Edit Add Remove Mark official

Tasks Edit Add Remove

Datasets Edit

Results from the Paper Edit

Methods Edit Add Remove

Code

Add Remove Mark official

Tasks

Add Remove

Datasets

Results from the Paper

Edit

Methods

Add Remove