SUMMARIST is an attempt to create a robust automated text summarization system, based on the ‘equation’: summarization = topic identification interpretation generation. Each of these stages contains several independent modules, many of them trained on large corpora of text. We describe the system’s architecture and provide details of some of its modules.

This thesis is an inquiry into the nature of the high-level, rhetorical structure of unrestricted natural language texts, computational means to enable its derivation, and two applications (in automatic summarization and natural language generation) that follow from the ability to build such structures automatically. The thesis proposes a first-order formalization of the high-level, rhetorical structure of text. The formalization assumes that text can be sequenced into elementary units; that discourse relations hold between textual units of various sizes; that some textual units are more important to the writer's purpose than others; and that trees are a good approximation of the abstract structure of text. The formalization also introduces a linguistically motivated compositionality criterion, which is shown to hold for the text structures that are valid. The thesis proposes, analyzes theoretically, and compares empirically four algorithms for determining the valid text structures of ...

. Health-education documents can be much more effective in achieving patient compliance if they are customized for individual readers. For this purpose, a medical record can be thought of as an extremely detailed user model of a reader of such a document. The HealthDoc project is developing methods for producing health-information and patienteducation documents that are tailored to the individual personal and medical characteristics of the patients who receive them. Information from an on-line medical record or from a clinician will be used as the primary basis for deciding how best to fit the document to the patient. In this paper, we describe our research on three aspects of the project: the kinds of tailoring that are appropriate for health-education documents; the nature of a tailorable master document, and how it can be created; and the linguistic problems that arise when a tailored instance of the document is to be generated. 1 The Value of Tailored Health-Education Documents He...

We present a new, data-driven approach to text planning, which can be used not only to map full knowledge pools into natural language texts, but also to generate texts that satisfy multiple, high-level communicative goals. The approach explains how global coherence can be achieved by exploiting the local coherence constraints of rhetorical relations. The local constraints were derived from a corpus analysis. Motivation 1 All current flexible approaches to text planning that assume that the abstract structure of text is a tree-like structure are, esentially, top-down approaches. Some of them define plan operators and exploit hierarchical planning techniques (Hovy 1993; Moore and Paris 1993; Moore and Swartout 1991; Cawsey 1991; Maybury 1992) and partial-order planning techniques (Young and Moore 1994). Others assume that plans are hierarchically organized sets of frames that can be derived through a top-down expansion process (Nirenburg et al. 1989; Meteer 1992). And the recursive app...

In this paper we compare performance of several heuristics in generating informative generic/query-oriented extracts for newspaper articles in order to learn how topic prominence affects the performance of each heuristic. We study how different query types can affect the performance of each heuristic and discuss the possibility of using machine learning algorithms to automatically learn good combination functions to combine several heuristics. We also briefly describe the design, implementation, and performance of a multilingual text summarization system SUMMARIST. Keywords Automated text summarization, topic extraction, summary evaluation. 1.

Our goal is to create an “intelligent” 3D agent able to send complex, ‘natural ’ messages to users and, in the future, to converse with them. We look at the relationship between the agent’s communicative intentions and the way that these intentions are expressed into verbal and nonverbal messages. In this paper, we concentrate on the study and generation of coordinated linguistic and gaze communicative acts. In this view we analyse gaze signals according to their functional meaning rather than to their physical actions. We propose a formalism where a communicative act is represented by two elements: a meaning (that corresponds to a set of goals and beliefs that the agent has the purpose to transmit to the interlocutor) and a signal, that is the nonverbal expression of that meaning. We also outline a methodology to generate messages that coordinate verbal with nonverbal signals.

Sentence planning is a set of inter-related but distinct tasks, one of which is sentence scoping, i.e. the choice of syntactic structure for elementary speech acts and the decision of how to combine them into one or more sentences. In this paper, we present SPoT, a sentence planner, and a new methodology for automatically training SPoT on the basis of feedback provided by human judges. We reconceptualize the task into two distinct phases. First, a very simple, randomized sentence-plangenerator (SPG) generates a potentially large list of possible sentence plans for a given text-plan input. Second, the sentence-plan-ranker (SPR) ranks the list of output sentence plans, and then selects the top-ranked plan. The SPR uses ranking rules automatically learned from training data. We show that the trained SPR learns to select a sentence plan whose rating on average is only 5% worse than the top human-ranked sentence plan. 1

This report presents a summary of the architectural characteristics of some of the Natural Language Generation (NLG) systems that serve as the main building blocks of the RAGS

this paper, on how such a trait may be rendered in automated NLG.

Abstract not found