Multilingual deep lexical acquisition for HPSGs via supertagging

Authors:
Phil Blunsom;Timothy Baldwin
Affiliations:
University of Melbourne, Victoria, Australia;University of Melbourne, Victoria, Australia
Venue:
EMNLP '06 Proceedings of the 2006 Conference on Empirical Methods in Natural Language Processing
Year:
2006

Citing 12
Cited 5

Markov random field models in computer vision

ECCV '94 Proceedings of the third European conference on Computer Vision (Vol. II)
Supertagging: an approach to almost parsing

Computational Linguistics
Parsing the wall street journal using a Lexical-Functional Grammar and discriminative estimation techniques

ACL '02 Proceedings of the 40th Annual Meeting on Association for Computational Linguistics
Transformation-based learning in the fast lane

NAACL '01 Proceedings of the second meeting of the North American Chapter of the Association for Computational Linguistics on Language technologies
Shallow parsing with conditional random fields

NAACL '03 Proceedings of the 2003 Conference of the North American Chapter of the Association for Computational Linguistics on Human Language Technology - Volume 1
Efficient deep processing of Japanese

COLING '02 Proceedings of the 3rd workshop on Asian language resources and international standardization - Volume 12
The grammar matrix: an open-source starter-kit for the rapid development of cross-linguistically consistent broad-coverage precision grammars

COLING-GEE '02 Proceedings of the 2002 workshop on Grammar engineering and evaluation - Volume 15
A comparison of algorithms for maximum entropy parameter estimation

COLING-02 proceedings of the 6th conference on Natural language learning - Volume 20
Error mining for wide-coverage grammar engineering

ACL '04 Proceedings of the 42nd Annual Meeting on Association for Computational Linguistics
The importance of supertagging for wide-coverage CCG parsing

COLING '04 Proceedings of the 20th international conference on Computational Linguistics
Wide-coverage semantic representations from a CCG parser

COLING '04 Proceedings of the 20th international conference on Computational Linguistics
Bootstrapping deep lexical resources: resources for courses

DeepLA '05 Proceedings of the ACL-SIGLEX Workshop on Deep Lexical Acquisition

Weakly supervised supertagging with grammar-informed initialization

COLING '08 Proceedings of the 22nd International Conference on Computational Linguistics - Volume 1
The Spanish resource grammar: pre-processing strategy and lexical acquisition

DeepLP '07 Proceedings of the Workshop on Deep Linguistic Processing
Faster parsing by supertagger adaptation

ACL '10 Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics
Grammar Customization

Research on Language and Computation
Parsing models for identifying multiword expressions

Computational Linguistics

Quantified Score

Hi-index	0.00

Visualization

Abstract

We propose a conditional random field-based method for supertagging, and apply it to the task of learning new lexical items for HPSG-based precision grammars of English and Japanese. Using a pseudo-likelihood approximation we are able to scale our model to hundreds of supertags and tens-of-thousands of training sentences. We show that it is possible to achieve start-of-the-art results for both languages using maximally language-independent lexical features. Further, we explore the performance of the models at the type- and token-level, demonstrating their superior performance when compared to a unigram-based baseline and a transformation-based learning approach.