Mark Kantrowitz and Joseph Bates. Integrated Natural Language Generation Systems, Technical Report CMU-CS-92-107, School of Computer Science, Carnegie Mellon University, Pittsburgh, PA, April 1992.  Home/Search   Document Details and Download   Summary   Related Articles   Check

....to encourage a certain type of behavior, or as overt as overriding their goals to force an action that is in the best interest of the overall story. Obviously the subtle approach is preferred. The challenges of presenting a compelling story in the face of interactivity are well documented [Bates, 1992], Murray, 1998] Weyhrauch, 1997] Mateas and Stem 2000] Szilas, 2001] A good story is well planned and scripted. The author goes to 4 great lengths to ensure events unfold in a sequence that best captures the author s desires and is interesting to the audience. In the case of an ....

....it was the first thorough treatment of the issues involved with developing an interactive story system. A research group at Carnegie Mellon University has an ongoing project to develop an interactive drama system that seamlessly combines believable agents with an interactive story structure [Bates, 1992], Kelso et al. 1993] Mateas, 1997] and [Mateas and Stem, 2000] This group, known as the Oz group, works with the overriding philosophy that drama is a combination of story, characters and presentation. They focus on building worlds that give equal attention to believable agents, interactive ....

[Article contains additional citation context not shown here]

Mark Kantrowitz and Joseph Bates. Integrated Natural Language Generation Systems, Technical Report CMU-CS-92-107, School of Computer Science, Carnegie Mellon University, Pittsburgh, PA, April 1992.

.... instead focus on explanation generation, creating scientific or instructional text which significantly differs in the distribution and frequency of syntactic, semantic, and orthographic features from that found in narrative prose (although a few projects do address some of these issues, e.g. [Kantrowitz and Bates, 1992; Robin, 1994; Doran, 1998; Cassell et al. 2000 ] In addition, the most advanced of these systems are still not capable of producing more than two paragraphs of text, while the vast majority of naturally occurring narratives are at least several pages long. Finally, none of these systems are ....

M. Kantrowitz and J. Bates. Integrated natural language generation systems. In R. Dale, E. Hovy, D. Rosner, and O. Stock, editors, Aspects of Automated Natural Language Generation, pages 247--262. Springer-Verlag, Berlin, 1992.

....is based on, ffl the computational formalisms that the system uses, ffl the social context and the field of text generation. According to the relation between the text planner and the generator (realizer) NLG systems are divided into three classes: pipelined, interleaved, and integrated (see [18]) In a pipelined system, the text planner produces the required information as input for the generator, and then the generator produces the worded text without any communication from the generator back to the planner. In contrast to the pipelined system, an interleaved system provides ....

....and generation stages are considered in a single formalism. A linguistic theory allows us to describe the resources of NL, and to construct a model that explains how NL transforms the semantic description into 1 More information about the current NLG systems and their approaches can be found in [4, 7, 18, 30, 32, 37]. CHAPTER 1. INTRODUCTION 3 a grammatical structure and its lexical items. Most of the current theories are only interested in syntax, morphology, or phonology, but not semantics or context [30] However, there is a strong relation between semantic and syntactic descriptions of NL. To represent ....

M. Kantrowitz and J. Bates. Integrated natural language generation systems. Technical Report CMU-CS-92-107, School of Computer Science, Carnegie Mellon University, Pittsburgh, April 1992.

..... 5 2 Different generator architectures [26] 8 3 The architecture of the TRIPS generator . 10 4 The generation process in GLINDA [44] . 11 5 The architecture of POPEL [86] 12 6 The generation framework [8] 21 7 Different communicative levels levels of planning ....

..... 59 23 The standard reference architecture [12] 61 24 WIP and PPP compared to the standard reference model [4] 62 List of Tables 1 Terms used to describe the two main parts aspects of NLG [26, 44] . 6 2 Example generation systems for different architectures . 9 3 Cohen and Perrault s REQUEST operator [20] 17 4 Grosz and Sidner vs. RST [75, 55] ....

[Article contains additional citation context not shown here]

Mark Kantrowitz and Joseph Bates. Integrated natural language generation systems. In Aspects of Automated Natural Language Generation. 6th International Workshop Proceedings, pages 13--28. Springer-Verlag, Berlin, Germany, 1992.

....a phrase structure grammar. Most current realization systems use unification grammars as their underlying mechanism. A common use for such grammars is enforcing number, gender, and case agreement. There has been interest in integrating the strategic and tactical sides of natural language generation[6]. Many of the tasks that a content planner and a surface realizer do are analogous. 1.2 Comparisons To Previous Work The approach here is similar to the Explainable Expert System (EES) Framework[12] however its model of query processing is built specifically to interpret CoBase operations. In ....

Kantrowitz, Mark and Bates, Joseph. 1992. Integrated Natural Language Generation Systems Aspects of Automated Natural Language Generation, Springer-Verlag.

....state graphically in accordance with familiar, intuitive metaphors. Yet in many instances we wish to grant systems broader, more complex responsibilities. Simple communication techniques are insufficient in these cases. If required, such systems must be able to explain themselves [7] 11] 10][6]. One area in which explanation technology is required is in Cooperative Information Systems[5] Traditionally database systems accept precise query specification (SQL, Datalog, etc. and return exact answer sets. In Cooperative Information Systems people pose imprecise queries and receive ....

Kantrowitz, Mark and Bates, Joseph. 1992. Integrated Natural Language Generation Systems Aspects of Automated Natural Language Generation, Springer-Verlag.

....kindly permitted by Kluwer Academic Publishers. 2 The theoretical feasibility of separating these tasks has often been questioned (e.g. by Danlos [1987] but practical generators that employ a truly integrated architecture have only been proposed recently (e.g. Ward 1991; Reithinger 1992; Kantrowitz and Bates 1992] Still, the major argument in favor of a two step, modular design is that it keeps control flow simple and separates the different knowledge sources involved. 3 For example, even in the seemingly innocent choice of prepositions, we notice stylistic differences like the Chapter 2. ....

M. Kantrowitz, J. Bates. "Integrated natural language generation systems. " In: R. Dale, E. Hovy, D. Rosner, O. Stock (eds.): Aspects of automated natural language generation -- Proceedings of the 6th International Workshop on Natural Language Generation. Berlin/Heidelberg: Springer, 1992.

....using a minimum of Hap specific terminology. We hope thereby to help suggest how other behavior based action architectures might be extended to support the production of language. We chose to base our language approach on the Glinda generator developed by Kantrowitz and Bates (Kantrowitz 1990; Kantrowitz Bates 1992) for three reasons. First, Glinda is an integrated generator (Kantrowitz Bates 1992) with the same generation engine used for both text planning and realization, and we saw similarities between the Hap execution engine and Glinda s generation engine that suggested that a fundamental merging ....

....other behavior based action architectures might be extended to support the production of language. We chose to base our language approach on the Glinda generator developed by Kantrowitz and Bates (Kantrowitz 1990; Kantrowitz Bates 1992) for three reasons. First, Glinda is an integrated generator (Kantrowitz Bates 1992), with the same generation engine used for both text planning and realization, and we saw similarities between the Hap execution engine and Glinda s generation engine that suggested that a fundamental merging might be possible. Second, Glinda outputs text incrementally, which we believe important ....

Kantrowitz, M., and Bates, J. 1992. Integrated natural language generation systems. In Dale, R.; Hovy, E.; Rosner, D.; and Stock, O., eds., Aspects of Automated Natural Language Generation, volume 587 of Lecture Notes in Artificial Intelligence, 13--28.

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC