Kees Van Deemter and Emiel Krahmer Graphs and Booleans: on the Generation of Referring Expressions
نویسنده
چکیده
Generation of Referring Expressions (gre) is a key task of Natural Language Generation nlg systems (e.g., Reiter and Dale, 2000, section 5.4). The task of a gre algorithm is to find combinations of properties that allow the generator to refer uniquely to an object or set of objects, called the target of the algorithm. Older gre algorithms tend to be based on a number of strongly simplifying assumptions. For example, they assume that the target is always one object (rather than a set), and they assume that properties can always only be conjoined, never negated or disjoined. Thus, for example, they could refer to a target object as “the small violinist”, but not as “the musicians not holding an instrument”. As a result of such simplifications, many current gre algorithms are logically incomplete. That is, they sometimes fail to find an appropriate description where one does exists.1 To remedy such limitations, various new algorithms have been proposed in recent years, each of which removes one or more simplifying assumptions. They extend existing gre algorithms by allowing targets that are sets (Stone, 2000; van Deemter, 2000), gradable properties (van Deemter, 2000, 2006), salience (Krahmer and Theune, 2002), relations between objects (Dale & Haddock, 1991; Horacek, 1997), and Boolean properties (van Deemter, 2001, 2002). Recently a new formalism, based on labelled directed graphs, was proposed as a vehicle for expressing and implementing different gre algorithms (Krahmer et al., 2001, 2003). Although the formalism was primarily argued to support relatively simple descriptions (not involving negations or disjunctions, for example), we will show that it can be used beyond these confines. Far from claiming that this will solve all the problems in this area, we do believe that a common formalism
منابع مشابه
Computational Generation of Referring Expressions: A Survey
This article offers a survey of computational research on referring expressions generation (REG). It introduces the REG problem and describes early work in this area, discussing what basic assumptions lie behind it, and showing how its remit has widened in recent years. We discuss computational frameworks underlying REG, and demonstrate a recent trend that seeks to link up REG algorithms with w...
متن کاملModels and Empirical Data for the Production of Referring Expressions
This paper introduces a special issue of Language, Cognition and Neuroscience dedicated to Production of Referring Expressions: Models and Empirical Data, focusing on models of reference production that make empirically testable predictions, as well as on empirical work that can inform the design of such models. In addition to introducing the volume, this paper also gives an overview of recent ...
متن کاملProduction of referring expressions: Preference trumps discrimination
When referring to an object using a description, speakers need to select properties which jointly distinguish it from any potential distractors. Previous empirical and computational work addressing this content selection process has highlighted the role of both (i) the discriminatory power of properties of a referent, i.e. how many of the distractors in a domain each property excludes; (ii) how...
متن کاملGenerating Expressions that Refer to Visible Objects
We introduce a novel algorithm for generating referring expressions, informed by human and computer vision and designed to refer to visible objects. Our method separates absolute properties like color from relative properties like size to stochastically generate a diverse set of outputs. Expressions generated using this method are often overspecified and may be underspecified, akin to expressio...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2008