Representing Knowledge for Planning Multisentential Text
نویسندگان
چکیده
The AlethGen tool has been used to build a system for automatically generating replies to complaints, for a European mail-order company. In the current version, letters are generated in French. AlethGen consists of several modules: the text deep structure planner (or conceptual planner), the text surface structure planner (or rhetorical planner), the computation of pronouns and quantifiers, and the linguistic generator proper (globally inspired by the Meaning-Text Theory) which determines the concrete realization of sentences. The paper mainly describes Ale thGen 's conceptual and rhetorical planners and focuses on the knowledge they use and produce. 1. Goals and general approach The main function of the texts we had to generate consisted indeed in replying to a complaint, thus in arguing and justifying a decision. This implies, on the one hand, a good management of the argumentative aspects, and on the other hand, the need to generate rather complex texts in a perfectly consistent style. The general approach of the conceptual planning is relation-based, as described in the Rhetorical Structure Theory or RST (Mann & Thompson, 1988). However, as shown in (Elhadad & Mc Keown, 1990), previous works in text generation systems (including RST) "have generally used a notion similar to rhetorical relations to descr ibe the connect ion between propositions. They make a one-to-one mapping from these relations to connectives for generation (for example, the "opposition" relation would be realized by the connective "but"). In this approach it is difficult to distinguish between similar connectives (e.g. [...] but vs. although)." In our work, we assume that there are two different levels of text structure. The deep level is represented by unordered basic relations, and the surface level is represented by (ordered) lists of atomic events and rhetorical operators.
منابع مشابه
Using Discourse Focus, Temporal Focus, and Spatial Focus to Generate Multisentential Text
This paper claims that reliance on discourse focus to guide the production of rhetorically structured texts is insufficient over lengthier stretches of prose. Instead, this paper argues that at least three distinct attentional constraints are required: discourse focus [Sidner, 1979, 1983; Grosz and Sidner, 1986], temporal focus [Webber, 1988], and a novel notion of spatial focus. The paper illu...
متن کاملDeveloping and Empirically Evaluating Robust Explanation Generators: The KNIGHT Experiments
To explain complex phenomena, an explanation system must be able to select information from a formal representation of domain knowledge, organize the selected information into multisentential discourse plans, and realize the discourse plans in text. Although recent years have witnessed significant progress in the development of sophisticated computational mechanisms for explanation, empirical r...
متن کاملConceptual Revision for Natural Language Generation
Traditional natural language generation systems are based on a pipelined architecture. A conceptual component selects items from a knowledge base and orders them into a message to address some discourse goal. This message is passed to the stylistic component that makes lexical and syntactic choices to produce a natural language surface text. By contrast, humans producing formal text typically c...
متن کاملThe Role of Underlying Structure in Text Generation
While a coherent organization is necessary for the generation of a multisentential paragraph, this organization itself conveys information, such as what knowledge is primary and what is secondary, and which of the various possible relationships between the pieces of knowledge the speaker wishes to make explicit. The organization of the message is an integral part of the message. Given this, it ...
متن کامل