Sciweavers

Free Online Productivity Tools i2Speak i2Symbol i2OCR iTex2Img iWeb2Print iWeb2Shot i2Type iPdf2Split iPdf2Merge i2Bopomofo i2Arabic i2Style i2Image i2PDF iLatex2Rtf Sci2ools

11

ACL
2015

favoriteEmaildiscussreport

29views Computational Linguistics» more ACL 2015»

Structured Training for Neural Network Transition-Based Parsing

8 years 13 days ago

Structured Training for Neural Network Transition-Based Parsing

Download www.petrovi.de

We present structured perceptron training for neural network transition-based dependency parsing. We learn the neural network representation using a gold corpus augmented by a large number of automatically parsed sentences. Given this ﬁxed network representation, we learn a ﬁnal layer using the structured perceptron with beam-search decoding. On the Penn Treebank, our parser reaches 94.26% unlabeled and 92.41% labeled attachment accuracy, which to our knowledge is the best accuracy on Stanford Dependencies to date. We also provide indepth ablative analysis to determine which aspects of our model provide the largest gains in accuracy.

David Weiss, Chris Alberti, Michael Collins, Slav

Real-time Traffic

ACL 2015 | Computational Linguistics |

claim paper

Related Content

» Parsing Embedded Clauses with Distributed Neural Networks

» FeasPar A Feature Structure Parser Learning to Parse Spoken Language

» A Constructive Approach to Parsing with Neural Networks The Hybrid Connectionist Parsing ...

» Neural Network Probability Estimation for Broad Coverage Parsing

» Effective Training Methods for Function Localization Neural Networks

» Discriminative Training of a Neural Network Statistical Parser

» A New Wavelet Back Propagation Neural Networks for Structural Dynamic Analysis

» The Growing Hierarchical SelfOrganizing Map

» Exploiting Event Semantics to Parse the Rhetorical Structure of Natural Language Text

» A neurodynamical model for working memory

Post Info
More Details (n/a)

Added	13 Apr 2016
Updated	13 Apr 2016
Type	Journal
Year	2015
Where	ACL
Authors	David Weiss, Chris Alberti, Michael Collins, Slav Petrov

Comments (0)