The limits on predictability and refinement of English structural annotation are examined by comparing independent annotations, by experienced analysts using the same detailed published guidelines, of a common sample of written texts. Three conclusions emerge. First, while it is not easy to define watertight boundaries between the categories of a comprehensive structural annotation scheme, limits on inter-annotator agreement are in practice set more by the difficulty of conforming to a well-defined scheme than by the difficulty of making a scheme well defined. Secondly, although usage is often structurally ambiguous, commonly the alternative analyses are logical distinctions without a practical difference – which raises questions about the role of grammar in human linguistic behaviour. Finally, one specific area of annotation is strikingly more problematic than any other area examined, though this area (classifying the functions of clause-constituents) seems a particularly significant one for human language use. These findings should be of interest both to computational linguists and to students of language as an aspect of human cognition.

For one aspect of grammatical annotation, part-of-speech tagging, we investigate experimentally whether the ceiling on accuracy stems from limits to the precision of tag definition or limits to analysts' ability to apply precise definitions, and we examine how analysts' performance is affected by alternative types of semi-automatic support. We find that, even for analysts very well-versed in a part-of-speech tagging scheme, human ability to conform to the scheme is a more serious constraint than precision of scheme definition. We also find that although semi-automatic techniques can greatly increase speed relative to manual tagging, they have little effect on accuracy, either positively (by suggesting valid candidate tags) or negatively (by lending an appearance of authority to incorrect tag assignments). On the other hand, it emerges that there are large differences between individual analysts with respect to usability of particular types of semi-automatic support.

The GEIG metric for quantifying the accuracy of parsing became influential through the Parseval programme, but many researchers have seen it as unsatisfactory. The Leaf-Ancestor (LA) metric, first developed in the 1980s, arguably comes closer to formalizing our intuitive concept of relative parse accuracy. We support this claim via an experiment that contrasts the performance of alternative metrics on the same body of automatically-parsed examples. The LA metric has the further virtue of providing straightforward indications of the location of parsing errors.