Generation of VP ellipsis: a corpus-based approach

Authors:
Daniel Hardt;Owen Rambow
Affiliations:
Copenhagen Business School, Copenhagen, Denmark;AT&T Labs -- Research, Florham Park, NJ
Venue:
ACL '01 Proceedings of the 39th Annual Meeting on Association for Computational Linguistics
Year:
2001

Citing 6
Cited 3

Assessing agreement on classification tasks: the kappa statistic

Computational Linguistics
Limited attention and discourse structure

Computational Linguistics
An empirical approach to VP ellipsis

Computational Linguistics
Applied text generation

ANLC '92 Proceedings of the third conference on Applied natural language processing
The effect of establishing coherence in ellipsis and anaphora resolution

ACL '93 Proceedings of the 31st annual meeting on Association for Computational Linguistics
Learning trees and rules with set-valued features

AAAI'96 Proceedings of the thirteenth national conference on Artificial intelligence - Volume 1

Squibs and discussions: human variation and lexical choice

Computational Linguistics - Summarization
Acquiring correct knowledge for natural language generation

Journal of Artificial Intelligence Research
Individual and domain adaptation in sentence planning for dialogue

Journal of Artificial Intelligence Research

Quantified Score

Hi-index	0.00

Visualization

Abstract

We present conditions under which verb phrases are elided based on a corpus of positive and negative examples. Factor that affect verb phrase ellipsis include: the distance between antecedent and ellipsis site, the syntactic relation between antecedent and ellipsis site, and the presence or absence of adjuncts. Building on these results, we examine where in the generation architecture a trainable algorithm for VP ellipsis should be located. We show that the best performance is achieved when the trainable module is located after the realizer and has access to surface-oriented features (error rate of 7.5%).