The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
This paper presents a methodology of specifying, controlling and synchronizing the temporal and spatial characteristics for 3D animation of facial expressions. The proposed approach consists of hierarchical levels of controls. The top level requires direct animator input of global abstract actions and their durations, which correspond to intuitive and natural specifications for facial animation. These...
Many existing natural language generation systems can be characterized according to their modularization as either pipelined or interleaved. In these separated systems, the generator is divided into several modules (e.g., planning and realization), with control and information passing between the modules during the generation process. This paper proposes a third type of generator, which we call integrated...
Augmenting the currently dominating view of text planning, which is essentially understood as planning the organization of a text's structure, this paper presents an approach that integrates this part of the generation process into a broader context. The influences of various conceptual and linguistic phenomena on a text's structure are examined: exploitation of conversational implicature, performing...
Research into natural language generation has often divided the processing into separate text planning and linguistic realization components. Despite this division's intuitive plausibility and practical utility, it ultimately interferes with some of the decisions necessary in the generation process. The IGEN generator, described here, implements a solution to this dilemma by having the linguistic...
We describe in this paper a new text planner that has been designed to address several problems we had encountered in previous systems. Motivating factors include a clearer and more explicit separation of the declarative and procedural knowledge used in a text generation system as well as the identification of the distinct types of knowledge necessary to generate coherent discourse, such as communicative...
We present a general solution to a common tactical problem, the contextsensitive suppression of redundant information. This solution is sensitive to unplanned, domain-specific inferences in the prior text. It employs a new, lexically grounded, conceptual representation for communicable information, which is part of a reversible model of how surface structures communicate information in naturally occurring...
Standard Functional Unification Grammars (FUGs) provide a structurally guided top-down control regime for sentence generation. When using FUGs to perform content realization as a whole, including lexical choice, this regime is no longer appropriate for two reasons: (1) the unification of non-lexicalized semantic input with an integrated lexico-grammar requires mapping “floating” semantic elements...
This paper clarifies the differences between structural and functional grammar theories from the viewpoint of syntactic selection in linguistic realization. Structural theories such as Context Free Grammar and Head-driven Phrase Structure Grammar are based on immediate dominance and linear precedence while functional theories such as Systemic Functional Grammar are based on functions and linear precedence...
In this document, we show how a constrained-based approach to lexical choice can overcome the problem of choosing lexical structures a priori and having to revise these judgements when more information is available. We focus on the treatment of linear precedence and on the determination of syntactic rules using a constraint logic programming approach.
This paper describes the language output component of the Sundial spoken dialogue system. Following a dialogue planning decision to produce an utterance, an utterance planning component derives a semantic description drawing on a model of speakers' knowledge of the domain. This semantic description is linguistically realised by a generation component which draws on a bi-directional lexicon-grammar...
This paper identifies a major problem in planning discourse, and then points to a solution. The problem is that of the relationship between models for monologue and dialogue. Rhetorical structure theory (RST) is selected as the current best prospect for modelling monologue. A model for exchange structure is then outlined — the systemic flowchart model — and we conclude by showing how the two can be...
We focus on the following question: given the causal and temporal relations between events in a knowledge base, what are the ways they can be described in extended text? We argue that we want to be able to generate laconic text, where certain temporal information remains implicit but pragmatically inferrable. An algorithm for generating laconic text is proposed, interleaving abduction and nonmonotonic...
We are currently engaged in a project to study the generation of instructional texts for common consumer devices. Our initial efforts have focused on an exhaustive corpus-based analysis of instruction booklets for cordless telephones. In this paper, we present our analysis of the way the various processes used in this domain are expressed. Our emphasis here is on the relationship between the surface...
Rhetorical Structure Theory (RST) has emerged as a promising candidate for text representation in NLG. We investigated the applicability of RST in the automatic production of multilingual technical manuals. Starting from a domain knowledge base, we construct an RST-tree for a particular manual section, which is then converted to a set of sentence plans. These plans serve as input to sentence generators...
To generate good text, many kinds of decisions should be made. Many researchers have spent much time searching for the architecture that would determine a proper order for these decisions. However, even if such an architecture is found, there are still certain kinds of problems that are difficult to consider during the generation process. Those problems can be more easily detected and solved by introducing...
This paper introduces the phenomena of transparently-motivated metaphor. It makes a case for its prevalence, and reports analysis of some of the textual goals that such metaphor can achieve. General principles that can explain many of the uses of metaphor are discussed. Our analysis of metaphors and the resulting principles have led to preliminary developments of a methodology for generating transparently-motivated...
EDWARD is a system which is being developed to study multimodal human-computer interaction. It incorporates a graph-editor called Gr2 and a Dutch natural language dialogue system called DoNaLD. EDWARD is capable of realizing referring actions in three ways: it can utter unimodal referring expressions, it can generate pointing gestures and it can produce multimodal referring expressions which combine...
In this paper, the performance of POPEL is demonstrated, an incremental and parallel natural language generation component for written German dialog contributions. The system's architectural approach is based on a cascaded model with feedback. It provides the flexibility essential for the integration into a dialog system. Furthermore, this architecture enables the seamless addition of the generation...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.