tailieunhanh - Báo cáo khoa học: "Structuring Knowledge for Reference Generation: A Clustering Algorithm"

This paper discusses two problems that arise in the Generation of Referring Expressions: (a) numeric-valued attributes, such as size or location; (b) perspective-taking in reference. Both problems, it is argued, can be resolved if some structure is imposed on the available knowledge prior to content determination. We describe a clustering algorithm which is sufficiently general to be applied to these diverse problems, discuss its application, and evaluate its performance. close’ on the given dimension, and ‘sufficiently distant’ from those of their distractors. . | Structuring Knowledge for Reference Generation A Clustering Algorithm Albert Gatt Department of Computing Science University of Aberdeen Scotland United Kingdom agatt@ Abstract This paper discusses two problems that arise in the Generation of Referring Expressions a numeric-valued attributes such as size or location b perspective-taking in reference. Both problems it is argued can be resolved if some structure is imposed on the available knowledge prior to content determination. We describe a clustering algorithm which is sufficiently general to be applied to these diverse problems discuss its application and evaluate its performance. 1 Introduction The problem of Generating Referring Expressions GRE can be summed up as a search for the properties in a knowledge base KB whose combination uniquely distinguishes a set of referents from their distractors. The content determination strategy adopted in such algorithms is usually based on the assumption made explicit in Reiter 1990 that the space of possible descriptions is partially ordered with respect to some principle s which determine their adequacy. Traditionally these principles have been defined via an interpretation of the Gricean maxims Dale 1989 Reiter 1990 Dale and Reiter 1995 van Deemter 2002 1. However little attention has been paid to contextual or intentional influences on attribute selection but cf. Jordan and Walker 2000 Krahmer and The-une 2002 . Furthermore it is often assumed that all relevant knowledge about domain objects is represented in the database in a format . attribute-value pairs that requires no further processing. This paper is concerned with two scenarios which raise problems for such an approach to GRE 1. Real-valued attributes . size or spatial coordinates which represent continuous dimensions. The utility of such attributes depends on whether a set of referents have values that are sufficiently 1For example the Gricean Brevity maxim Grice 1975 has been interpreted