Specifying a shallow grammatical representation for parsing purposes
摘要
Is it possible to specify a grammatical representation (descriptors and their application guidelines) to such a degree that it can be consistently applied by different grammarians e.g. for producing a benchmark corpus for parser evaluation? Arguments for and against have been given, but very little empirical evidence. In this article we report on a double-blind experiment with a surface-oriented morphosyntactic grammatical representation used in a large-scale English parser. We argue that a consistently applicable representation for morphology and also shallow syntax can be specified. A grammatical representation with a near-100% coverage of running text can be specified with a reasonable effort, especially if the representation is based on structural distinctions (i.e. it is structurally resolvable).
引用
@article{arxiv.cmp-lg/9502011,
title = {Specifying a shallow grammatical representation for parsing purposes},
author = {Atro Voutilainen and Timo Jarvinen},
journal= {arXiv preprint arXiv:cmp-lg/9502011},
year = {2016}
}
备注
EACL95, uuencoded and gzipped .ps