There are obvious reasons for trying to automate the production of multilingual documen- tation, especially for routine subject-matter in restricted domains (e.g. technical instructions). Two approaches have been adopted: Machine Translation (MT) of a source text, and Multilingual Natural Language Generation (M-NLG) from a knowledge base. For MT, information extraction is a major difficulty, since the meaning must be derived by analysis of the source text; M-NLG avoids this difficulty but seems at first sight to require an expensive phase of knowledge engineering in order to encode the meaning. We introduce here a new technique which employs M-NLG during the phase of knowledge editing. A 'feedback text', generated from a possibly incomplete knowledge base, describes in natural language the knowledge encoded so far, and the options for extending it. This method allows anyone speaking one of the supported languages to produce texts in all of them, requiring from the author only expertise in the subject-matter, not expertise in knowledge engineering.

Many kinds of knowledge-based system would be easier to develop and maintain if domain experts (as opposed to knowledge engineers) were in a position to define and edit the knowledge. From the viewpoint of domain experts, the best medium for defining the knowledge would be a text in natural language; however, natural language input cannot be decoded reliably unless written in controlled languages, which are difficult for domain experts to learn and use. WYSIWYM editing is an alternative solution in which the texts employed to view and edit the knowledge are generated not by the user but by the system. The user can add knowledge by clicking on `anchors' in the text and choosing from a list of semantic alternatives; each choice directly updates the knowledge base, from which a new text is then generated. 1 KNOWLEDGE EDITING Many applications require editing of information expressed in a knowledge representation formalism. Expert systems are an obvious example; others are systems for gen...

Natural language generation technology is now ripe for commercial exploitation, but one of the remaining bottlenecks is that of providing NLG systems with user-friendly interfaces for specifying the content of documents to be generated. We present here a new technique we have developed for providing such interfaces: WYSIWYM editing. WYSIWYM (What You See Is What You Meant) makes novel use of the system's generator to provide a natural language input device which requires no NL interpretation --- only NL generation.

... document structure can be seen as an extension of Nunberg's `text-grammar'; it is also closely related to `logical' mark-up in languages like HTML and LATEX. We show that by using this intermediate representation, several subtasks in language generation and language understanding can be defined more cleanly.

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

Discourse markers ('cue words') are lexical items that signal the kind of coherence relation holding between adjacent text spans; for example, because, since, and for this reason are dif- ferent markers for causal relations. Discourse markers are a syntactically quite heterogeneous group of words, many of which are traditionally treated as function words belonging to the realm of grammar rather than to the lexicon. But for a single discourse relation there is often a set of similar markers, allowing for a range of paraphrases for expressing the relation. To capture the similarities and differences between these, and to represent them adequately, we are developing DiMLex, a lexicon of discourse markers. After describing our methodology and the kind of information to be represented in DiMLex, we briefly discuss its potential applications in both text generation and understanding.

This paper briefly outlines the WYSIWYM (What You See is What You Meant) approach to knowledge editing and focuses on the role of coreferring Noun Phrases in the feedback texts that are generated by a WYSIWYM system and which play a key role in this approach. The paper pays special attention to the operations that a user of a WYSIWYM system can perform on feedback texts that contain coreferring Noun Phrases and to how they can be supported.

We present the rags (Reference Architecture for Generation Systems) framework: a specification of an abstract Natural Language Generation (NLG) system architecture to support sharing, re-use, comparison and evaluation of NLG technologies. We argue that the evidence from a survey of actual NLG systems calls for a different emphasis in a reference proposal from that seen in similar initiatives in information extraction and multimedia interfaces. We introduce the framework itself, in particular the two-level data model that allows us to support the complex data requirements of NLG systems in a flexible and coherent fashion, and describe our efforts to validate the framework through a range of implementations.

Abstract not found

Automated text generation requires a underlying knowledge base from whieh to generate, which is often difficult to produce. Software documentation is one domain in which parts of this knowledge base may be derived automatically. In this paper, we describe I)RAFTER, an authoring support tool for generating usercentred softwm-e documentation, and in particular, we describe how parts of its required knowledge base can be obtained automatically.