Efficient Structured Inference for Transition-Based Parsing with Neural Networks and Error States (2016-06-02T00:00:00.000000Z)

TL;DR

This paper proposes a new approach for approximate structured inference for transition-based parsing that produces scores suitable for global scoring using local models with the introduction of error states in local training.

Abstract

Transition-based approaches based on local classification are attractive for dependency parsing due to their simplicity and speed, despite producing results slightly below the state-of-the-art. In this paper, we propose a new approach for approximate structured inference for transition-based parsing that produces scores suitable for global scoring using local models. This is accomplished with the introduction of error states in local training, which add information about incorrect derivation paths typically left out completely in locally-trained models. Using neural networks for our local classifiers, our approach achieves 93.61% accuracy for transition-based dependency parsing in English.

Authors

Ashish Vaswani

4 papers

Kenji Sagae

3 papers

TL;DR

Abstract

Authors

References39 items

Incremental Recurrent Neural Network Dependency Parser with Search-based Discriminative Training

Structured Training for Neural Network Transition-Based Parsing

Enforcing Structural Diversity in Cube-pruned Dependency Parsing

Training Deterministic Parsers with Non-Deterministic Oracles

Optimal Incremental Parsing via Best-First Dynamic Programming

Decoding with Large-Scale Neural Language Models Improves Translation

Turning on the Turbo: Fast Third-Order Non-Projective Turbo Parsers

A Non-Monotonic Arc-Eager Transition System for Dependency Parsing

A Dynamic Oracle for Arc-Eager Dependency Parsing

Incremental Joint Approach to Word Segmentation, POS Tagging, and Dependency Parsing in Chinese

Improving neural networks by preventing co-adaptation of feature detectors

Structured Perceptron with Inexact Search

Transition-based Dependency Parsing with Rich Non-local Features

Getting the Most out of Transition-based Dependency Parsing

Natural Language Processing (Almost) from Scratch

Adaptive Subgradient Methods for Online Learning and Stochastic Optimization

A Reduction of Imitation Learning and Structured Prediction to No-Regret Online Learning

Dynamic Programming for Linear-Time Incremental Parsing

Rectified Linear Units Improve Restricted Boltzmann Machines

Search-based structured prediction

Algorithms for Deterministic Incremental Dependency Parsing

A Tale of Two Parsers: Investigating and Combining Graph-based and Transition-based Dependency Parsing

The Stanford Typed Dependencies Representation

Simple Semi-supervised Dependency Parsing

The CoNLL 2007 Shared Task on Dependency Parsing

Dependency Parsing and Domain Adaptation with LR Models and Parser Ensembles

Investigating Multilingual Dependency Parsing

Deterministic Dependency Parsing of English Text

Incremental Parsing with the Perceptron Algorithm

Statistical Dependency Analysis with Support Vector Machines

Discriminative Training Methods for Hidden Markov Models: Theory and Experiments with Perceptron Algorithms

Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data

Maximum Entropy Markov Models for Information Extraction and Segmentation

Building a Large Annotated Corpus of English: The Penn Treebank

Class-Based n-gram Models of Natural Language

A Fast and Accurate Dependency Parser using Neural Networks

BLLIP 1987-89 WSJ corpus release 1

NAACL HLT ’12

of the Association for Computational Linguistics

Field of Study

Journal Information

Name

Page

Volume

Venue Information

Name

Type

URL

Alternate Names