Robust PCFG-based generation using automatically acquired LFG approximations

Authors:
Aoife Cahill;Josef van Genabith
Affiliations:
Dublin City University, Dublin, Ireland;Dublin City University, Dublin, Ireland and Center for Advanced Studies, IBM Dublin, Ireland
Venue:
ACL-44 Proceedings of the 21st International Conference on Computational Linguistics and the 44th annual meeting of the Association for Computational Linguistics
Year:
2006

Citing 13
Cited 22

Estimating lexical priors for low-frequency morphologically ambiguous forms

Computational Linguistics
Stochastic attribute-value grammars

Computational Linguistics
Forest-based statistical sentence generation

NAACL 2000 Proceedings of the 1st North American chapter of the Association for Computational Linguistics conference
Trainable methods for surface natural language generation

NAACL 2000 Proceedings of the 1st North American chapter of the Association for Computational Linguistics conference
Chart generation

ACL '96 Proceedings of the 34th annual meeting on Association for Computational Linguistics
Exploiting a probabilistic hierarchical model for generation

COLING '00 Proceedings of the 18th conference on Computational linguistics - Volume 1
LFG generation produces context-free languages

COLING '00 Proceedings of the 18th conference on Computational linguistics - Volume 1
BLEU: a method for automatic evaluation of machine translation

ACL '02 Proceedings of the 40th Annual Meeting on Association for Computational Linguistics
The Penn Treebank: annotating predicate argument structure

HLT '94 Proceedings of the workshop on Human Language Technology
Long-distance dependency resolution in automatically acquired wide-coverage PCFG-based LFG approximations

ACL '04 Proceedings of the 42nd Annual Meeting on Association for Computational Linguistics
Evaluating coverage for large symbolic NLG grammars

IJCAI'03 Proceedings of the 18th international joint conference on Artificial intelligence
Probabilistic models for disambiguation of an HPSG-based chart generator

Parsing '05 Proceedings of the Ninth International Workshop on Parsing Technology
High efficiency realization for a wide-coverage unification grammar

IJCNLP'05 Proceedings of the Second international joint conference on Natural Language Processing

Dependency-based n-gram models for general purpose sentence realisation

COLING '08 Proceedings of the 22nd International Conference on Computational Linguistics - Volume 1
Stochastic realisation ranking for a free word order language

ENLG '07 Proceedings of the Eleventh European Workshop on Natural Language Generation
Sentence realisation from bag of words with dependency constraints

SRWS '09 Proceedings of Human Language Technologies: The 2009 Annual Conference of the North American Chapter of the Association for Computational Linguistics, Companion Volume: Student Research Workshop and Doctoral Consortium
Automatic treebank-based acquisition of Arabic LFG dependency structures

Semitic '09 Proceedings of the EACL 2009 Workshop on Computational Approaches to Semitic Languages
An investigation into the validity of some metrics for automatically evaluating natural language generation systems

Computational Linguistics
Dependency based Chinese sentence realization

ACL '09 Proceedings of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language Processing of the AFNLP: Volume 2 - Volume 2
Practical grammar-based NLG from examples

INLG '08 Proceedings of the Fifth International Natural Language Generation Conference
Accurate and robust LFG-based generation for Chinese

INLG '08 Proceedings of the Fifth International Natural Language Generation Conference
Parser-based retraining for domain adaptation of probabilistic generators

INLG '08 Proceedings of the Fifth International Natural Language Generation Conference
A Linguistically Inspired Statistical Model for Chinese Punctuation Generation

ACM Transactions on Asian Language Information Processing (TALIP)
A simple domain-independent probabilistic approach to generation

EMNLP '10 Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing
Towards an extrinsic evaluation of referring expressions in situated dialogs

INLG '10 Proceedings of the 6th International Natural Language Generation Conference
Finding common ground: towards a surface realisation shared task

INLG '10 Proceedings of the 6th International Natural Language Generation Conference
Introducing shared tasks to NLG: the TUNA shared task evaluation challenges

Empirical methods in natural language generation
A translation from logic to English with dynamic semantics

JSAI-isAI'09 Proceedings of the 2009 international conference on New frontiers in artificial intelligence
Designing agreement features for realization ranking

COLING '10 Proceedings of the 23rd International Conference on Computational Linguistics: Posters
Dependency-based n-gram models for general purpose sentence realisation

Natural Language Engineering
Glue rules for robust chart realization

ENLG '11 Proceedings of the 13th European Workshop on Natural Language Generation
The first surface realisation shared task: overview and evaluation results

ENLG '11 Proceedings of the 13th European Workshop on Natural Language Generation
DCU*at generation challenges 2011 surface realisation track

ENLG '11 Proceedings of the 13th European Workshop on Natural Language Generation
Lfg generation by grammar specialization

Computational Linguistics
A task-performance evaluation of referring expressions in situated collaborative task dialogues

Language Resources and Evaluation

Quantified Score

Hi-index	0.00

Visualization

Abstract

We present a novel PCFG-based architecture for robust probabilistic generation based on wide-coverage LFG approximations (Cahill et al., 2004) automatically extracted from treebanks, maximising the probability of a tree given an f-structure. We evaluate our approach using string-based evaluation. We currently achieve coverage of 95.26%, a BLEU score of 0.7227 and string accuracy of 0.7476 on the Penn-II WSJ Section 23 sentences of length ≤20.