Entity-based local coherence modelling using topological fields

Authors:
Jackie Chi Kit Cheung;Gerald Penn
Affiliations:
University of Toronto, Toronto, ON, Canada;University of Toronto, Toronto, ON, Canada
Venue:
ACL '10 Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics
Year:
2010

Citing 15
Cited 3

Learning to Classify Text Using Support Vector Machines: Methods, Theory and Algorithms

Learning to Classify Text Using Support Vector Machines: Methods, Theory and Algorithms
Functional centering: grounding referential coherence in information structure

Computational Linguistics
Improving machine learning approaches to coreference resolution

ACL '02 Proceedings of the 40th Annual Meeting on Association for Computational Linguistics
Probabilistic text structuring: experiments with sentence ordering

ACL '03 Proceedings of the 41st Annual Meeting on Association for Computational Linguistics - Volume 1
Optimizing Referential Coherence in Text Generation

Computational Linguistics
Centering: A Parametric Theory and Its Instantiations

Computational Linguistics
Automatic Evaluation of Information Ordering: Kendall's Tau

Computational Linguistics
The German Vorfeld and Local Coherence

Journal of Logic, Language and Information
Modeling local coherence: An entity-based approach

Computational Linguistics
Evaluating centering for information ordering using corpora

Computational Linguistics
BART: a modular toolkit for coreference resolution

HLT-Demonstrations '08 Proceedings of the 46th Annual Meeting of the Association for Computational Linguistics on Human Language Technologies: Demo Session
Estimation of conditional probabilities with decision trees and an application to fine-grained POS tagging

COLING '08 Proceedings of the 22nd International Conference on Computational Linguistics - Volume 1
Extending the entity-grid coherence model to semantically related entities

ENLG '07 Proceedings of the Eleventh European Workshop on Natural Language Generation
Inferring strategies for sentence ordering in multidocument news summarization

Journal of Artificial Intelligence Research
Topological field parsing of German

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 1 - Volume 1

Extending the entity grid with entity-specific features

HLT '11 Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies: short papers - Volume 2
Extending the entity-based coherence model with multiple ranks

EACL '12 Proceedings of the 13th Conference of the European Chapter of the Association for Computational Linguistics
To what extent does sentence-internal realisation reflect discourse context?: a study on word order

EACL '12 Proceedings of the 13th Conference of the European Chapter of the Association for Computational Linguistics

Quantified Score

Hi-index	0.00

Visualization

Abstract

One goal of natural language generation is to produce coherent text that presents information in a logical order. In this paper, we show that topological fields, which model high-level clausal structure, are an important component of local coherence in German. First, we show in a sentence ordering experiment that topological field information improves the entity grid model of Barzilay and Lapata (2008) more than grammatical role and simple clausal order information do, particularly when manual annotations of this information are not available. Then, we incorporate the model enhanced with topological fields into a natural language generation system that generates constituent orders for German text, and show that the added coherence component improves performance slightly, though not statistically significantly.