The process of microplanning encompasses a range of problems in Natural Language Generation (NLG), such as referring expression generation, lexical choice, and aggregation, problems in which a generator must bridge underlying domain-specific representations and general linguistic representations. In this paper, we describe a uniform approach to microplanning based on declarative representations of a generator's communicative intent. These representations describe the RE- SULTS of NLG: communicative intent associates the concrete linguistic structure planned by the generator with inferences that show how the meaning of that structure communicates needed information about some application domain in the current discourse context. Our approach, implemented in the SPUD (sentence planning using description) microplanner, uses the lexicalized treeadjoining grammar formalism (LTAG) to connect structure to meaning and uses modal logic programming to connect meaning to context. At the same time, communicative intent representations provide a RESOURCE for the PROCESS of NLG. Using representations of communicative intent, a generator can augment the syntax, semantics and pragmatics of an incomplete sentence simultaneously, and can assess its progress on the various problems of microplanning incrementally. The declarative formulation of communicative intent translates into a well-defined methodology for designing grammatical and conceptual resources which the generator can use to achieve desired microplanning behavior in a specified domain. Contents 1 Motivation 3 2

This paper describes PEBA-II, a working natural language generation system which interactively describes animals in a taxonomic knowledge base via the production of World Wide Web pages. Our aim is to construct a natural language document generation system with real practical applicability: to this end, the system reconstructs and combines a number of existing ideas in the literature in a novel way, and proposes a solution to the problem of breadth of coverage that is based on a pragmatic approach to knowledge representation and linguistic realisation. The system embodies the following features: ffl a reconstruction of some of the core ideas in schema--based text generation [McKeown 1985], applied to the generation of hypertext documents; ffl the principled use of a phrasal lexicon to ease surface generation, in concert with a knowledge base whose elements may correspond to pre--compiled collections of atomic units; ffl a user model and discourse model that permit interesting varia...

Intensive care is becoming increasingly complex. If mistakes are to be avoided, there is a need for the large amount of clinical data to be presented effectively to the medical staff. Although the most common approach is to present the data graphically, it has been shown that textual summarisation can lead to improved decision making. As the first step in the BabyTalk project, a prototype is being developed which will generate a textual summary of 45 minutes of continuous physiological signals and discrete events (e.g.: equipment settings and drug administration). Its architecture brings together techniques from the different areas of signal analysis, medical reasoning, and natural language generation. Although the current system is still being improved, it is powerful enough to generate meaningful texts containing the most relevant information. This prototype will be extended to summarize several hours of data and to include clinical interpretation. 1

The incremental algorithm introduced in (Dale and Reiter, 1995) for producing distinguishing descriptions does not always generate a minimal description. In this paper, I show that when generalised to sets of individuals and disjunctive properties, this approach might generate unnecessarily long and ambiguous and/or epistemically redundant descriptions. I then present an alternative, constraint-based algorithm and show that it builds on existing related algorithms in that (i) it produces minimal descriptions for sets of individuals using positive, negative and disjunctive properties, (ii) it straightforwardly generalises to n-ary relations and (iii) it is integrated with surface realisation.

A fundamental requirement of any task-oriented dialogue system is the ability to generate object descriptions that refer to objects in the task domain. The subproblem of content selection for object descriptions in task-oriented dialogue has been the focus of much previous work and a large number of models have been proposed. In this paper, we use the annotated coconut corpus of task-oriented design dialogues to develop feature sets based on Dale and Reiter’s (1995) incremental model, Brennan and Clark’s (1996) conceptual pact model, and Jordan’s (2000b) intentional influences model, and use these feature sets in a machine learning experiment to automatically learn a model of content selection for object descriptions. Since Dale and Reiter’s model requires a representation of discourse structure, the corpus annotations are used to derive a representation based on Grosz and Sidner’s (1986) theory of the intentional structure of discourse, as well as two very simple representations of discourse structure based purely on recency. We then apply the rule-induction program ripper to train and test the content selection component of an object description generator on a set of 393 object descriptions from the corpus. To our

In this paper, we describe the Rich Representation Language (RRL) which is used in the NECA system. The NECA system generates interactions between two or more animated characters. The RRL is a formal framework for representing the information that is exchanged at the interfaces between the various NECA system modules.

A spoken language generation system has been developed that learns to describe objects in computer-generated visual scenes. The system is trained by a `show-and-tell' procedure in which visual scenes are paired with natural language descriptions. Learning algorithms acquire probabilistic structures which encode the visual semantics of phrase structure, word classes, and individual words. Using these structures, a planning algorithm integrates syntactic, semantic, and contextual constraints to generate natural and unambiguous descriptions of objects in novel scenes.

In this paper we tackle the problem of generating natural route descriptions on the basis of input obtained from a commercially available way-finding system. Our framework and architecture incorporates the use of general principles drawn from the domain of natural language generation. Through examples we demonstrate that it is possible to bridge the gap between underlying data representations and natural sounding linguistic descriptions. The work presented contributes both to the area of natural language generation and to the improvement of way-finding system interfaces.

We envisage a novel computer tool for producing technical documentation, in which the author specifies the desired content and style, but the exact wording and layout i s determined by the system (including versions in languages the author need not know ); a prototype of such a system is being developed in the ICONOCLAST project. Amongs t other things, the system must adapt the wording of the generated document to its punctuation and layout. By studying a corpus of patient information leaflets, we have found many detailed examples of this interaction, some of which are described here. In particular, we focus on ways in which the use of special layout patterns (e.g., vertical lists, boxes) changes the options for wording, sometimes licensing departures from normal conventions of grammar and punctuation. 1

We present a data-to-speech system called D2S, which can be used for the creation of datato -speech systems in different languages and domains. The most important characteristic of a data-to-speech system is that it combines language and speech generation: language generation is used to produce a natural language text expressing the system's input data, and speech generation is used to make this text audible. In D2S, this combination is exploited by using linguistic information available in the language generation module for the computation of prosody. This allows us to achieve a better prosodic output quality than can be achieved in a plain text-to-speech system. For language generation in D2S, the use of syntactically enriched templates is guided by knowledge of the discourse context, while for speech generation pre-recorded phrases are combined in a prosodically sophisticated manner. This combination of techniques makes it possible to create linguistically sound but efficient system...