Combine constituent and dependency parsing via reranking

Authors:
Xiaona Ren;Xiao Chen;Chunyu Kit
Affiliations:
Department of Chinese, Translation and Linguistics, City University of Hong Kong, Kowloon, HKSAR, China;Department of Chinese, Translation and Linguistics, City University of Hong Kong, Kowloon, HKSAR, China and SOGOU-INC, Beijing, China;Department of Chinese, Translation and Linguistics, City University of Hong Kong, Kowloon, HKSAR, China
Venue:
IJCAI'13 Proceedings of the Twenty-Third international joint conference on Artificial Intelligence
Year:
2013

Citing 28
Cited 0

Training products of experts by minimizing contrastive divergence

Neural Computation
Discriminative Reranking for Natural Language Parsing

ICML '00 Proceedings of the Seventeenth International Conference on Machine Learning
Building a large annotated corpus of English: the penn treebank

Computational Linguistics - Special issue on using large corpora: II
A maximum-entropy-inspired parser

NAACL 2000 Proceedings of the 1st North American chapter of the Association for Computational Linguistics conference
Japanese dependency structure analysis based on maximum entropy models

EACL '99 Proceedings of the ninth conference on European chapter of the Association for Computational Linguistics
Three generative, lexicalised models for statistical parsing

ACL '98 Proceedings of the 35th Annual Meeting of the Association for Computational Linguistics and Eighth Conference of the European Chapter of the Association for Computational Linguistics
An efficient implementation of a new DOP model

EACL '03 Proceedings of the tenth conference on European chapter of the Association for Computational Linguistics - Volume 1
Intricacies of Collins' Parsing Model

Computational Linguistics
Japanese dependency structure analysis based on support vector machines

EMNLP '00 Proceedings of the 2000 Joint SIGDAT conference on Empirical methods in natural language processing and very large corpora: held in conjunction with the 38th Annual Meeting of the Association for Computational Linguistics - Volume 13
Discriminative training methods for hidden Markov models: theory and experiments with perceptron algorithms

EMNLP '02 Proceedings of the ACL-02 conference on Empirical methods in natural language processing - Volume 10
Discriminative training of a neural network statistical parser

ACL '04 Proceedings of the 42nd Annual Meeting on Association for Computational Linguistics
Online large-margin training of dependency parsers

ACL '05 Proceedings of the 43rd Annual Meeting on Association for Computational Linguistics
Coarse-to-fine n-best parsing and MaxEnt discriminative reranking

ACL '05 Proceedings of the 43rd Annual Meeting on Association for Computational Linguistics
Non-projective dependency parsing using spanning tree algorithms

HLT '05 Proceedings of the conference on Human Language Technology and Empirical Methods in Natural Language Processing
TAG, dynamic programming, and the perceptron for efficient, feature-rich parsing

CoNLL '08 Proceedings of the Twelfth Conference on Computational Natural Language Learning
Stacking dependency parsers

EMNLP '08 Proceedings of the Conference on Empirical Methods in Natural Language Processing
A tale of two parsers: investigating and combining graph-based and transition-based dependency parsing using beam-search

EMNLP '08 Proceedings of the Conference on Empirical Methods in Natural Language Processing
Two languages are better than one (for syntactic parsing)

EMNLP '08 Proceedings of the Conference on Empirical Methods in Natural Language Processing
Combining constituent parsers

NAACL-Short '09 Proceedings of Human Language Technologies: The 2009 Annual Conference of the North American Chapter of the Association for Computational Linguistics, Companion Volume: Short Papers
An empirical study of semi-supervised structured conditional models for dependency parsing

EMNLP '09 Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing: Volume 2 - Volume 2
K-best combination of syntactic parsers

EMNLP '09 Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing: Volume 3 - Volume 3
Products of random latent variable grammars

HLT '10 Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics
Efficient third-order dependency parsers

ACL '10 Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics
Dependency parsing and projection based on word-pair classification

ACL '10 Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics
Self-training with products of latent variable grammars

EMNLP '10 Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing
Features for phrase-structure reranking from dependency parses

IWPT '11 Proceedings of the 12th International Conference on Parsing Technologies
Hybrid combination of constituency and dependency trees into an ensemble dependency parser

HYBRID '12 Proceedings of the Workshop on Innovative Hybrid Approaches to the Processing of Textual Data
Higher-order constituent parsing and parser combination

ACL '12 Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics: Short Papers - Volume 2

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents a reranking approach to combining constituent and dependency parsing, aimed at improving parsing performance on both sides. Most previous combination methods rely on complicated joint decoding to integrate graph- and transition-based dependency models. Instead, our approach makes use of a high-performance probabilistic context free grammar (PCFG) model to output k-best candidate constituent trees, and then a dependency parsing model to rerank the trees by their scores from both models, so as to get the most probable parse. Experimental results show that this reranking approach achieves the highest accuracy of constituent and dependency parsing on Chinese treebank (CTB5.1) and a comparable performance to the state of the art on English treebank (WSJ).