Generation of VP Ellipsis: A Corpus-Based Approach
35229Authors
nan
Abstract
We present conditions under which verb phrases are elided based on a cor- pus of positive and negative examples. Factor that affect verb phrase ellipsis in- clude: 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 exam- ine where in the generation architec- ture a trainable algorithm for VP ellip- sis 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%). 1
Keywords
Full Content
Generation of VP Ellipsis: A Corpus-Based Approach Daniel Hardt Copenhagen Business School Copenhagen, Denmark dh@id.cbs.dk Owen Rambow AT&T Labs – Research Florham Park, NJ, USA rambow@research.att.com Abstract We present conditions under which verb phrases are elided based on a cor- pus of positive and negative examples. Factor that affect verb phrase ellipsis in- clude: 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 exam- ine where in the generation architec- ture a trainable algorithm for VP ellip- sis 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%). 1 Introduction While there is a vast theoretical and computa- tional literature on the interpretation of elliptical forms, there has been little study of the generation of ellipsis.1 In this paper, we focus on Verb Phase Ellipsis (VPE), in which a verb phrase is elided, with an auxiliary verb left in its place. Here is an example: (1) In 1980, 18% of federal prosecutions con- cluded at trial; in 1987, only 9% did. Here, the verb phase concluded at trial is omit- ted, and the auxiliary did appears in its place. The 1We would like to thank Marilyn Walker, three review- ers for a previous submission, and three reviewers for this submission for helpful comments. basic condition on VPE is clear from the litera- ture:2 there must be an antecedent VP that is iden- tical in meaning to the elided VP. Furthermore, it seems clear that the antecedent must be suffi- ciently close to the ellipsis site (in a sense to be made precise). This basic condition provides a beginning of an account of the generation of VPE. However, there is more to be said, as is shown by the following examples: (2) Ernst & Young said Eastern’s plan would miss projections by $100 million. Goldman said Eastern would miss the same mark by at least $120 million. In this example, the italicized VP could be elided, since it has a nearby antecedent (in bold) with the same meaning. Indeed the antecedents in this example is closer than in the following exam- ple in which ellipsis does occur: (3) In particular Mr Coxon says businesses are paying out a smaller percentage of their profits and cash flow in the form of dividends than they have VPE historically. In this paper, we identify factors which govern the decision to elide VPs. We examine a corpus of positive and negative examples; i.e., examples in which VPs were or were not elided. We find that, indeed, the distance between ellipsis site and an- tecedent is correlated with the decision to elide, as are the syntactic relation between antecedent 2The classic study is (Sag, 1976); for more recent work, see, eg, (Dalrymple et al., 1991; Kehler, 1993; Fiengo and May, 1994; Hardt, 1999). and ellipsis site, and …
Content truncated to 500 words
Labeled Text
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 surfaceoriented features (error rate of 7.5%). 1
Publication Details
- Paper ID:
- 35229
- Year:
- 2001
- Publication:
- TIPSTER
- Publication Type:
- conf
- DOI:
- nan