This paper describes the linguistic part of a system called PROVERB, which transforms, abstracts, and verbalizes machine-found proofs into formated texts. Linguistically, the architecture of PROVERB follows most application oriented systems, and is a pipe-lined control of three components. Its macroplanner linearizes a proof and plans mediating communicative acts by employing a combination of hierarchical planning and focus-guided navigation. The microplanner

We argue in this paper that sophisticated microplanning techniques are required even for mathematical proofs, in contrast to the belief that mathematical texts are only schematic and mechanical. We demonstrate why paraphrasing and aggregation significantly enhance the flexibility and the coherence of the text produced. To this end, we adopted the Text Structure of Meteer as our basic representation. The type checking mecha- nism of Text Structure allows us to achieve paraphrasing by building comparable combinations of linguistic resources. Specified in terms of concepts in an uniform ontological structure called the Upper Model, our semantic aggregation rules are more compact than similar rules reported in the literature.

A natural language generation system is typically constituted by two main components: a content planning component (e.g., text planner or dialogue act planner) and a linguistic realization component. But, this is not sufficient since, on the one hand, the message built by the content planning component is generally not adequately detailed in order to control the many possibilities for its expression and, on the other hand, the content planner cannot influence the way in which the message will be verbalized. Generation systems

This paper outlines the microplanner of PROVERB , a system that generates multilingual text from machine-found mathematical proofs. The main representational vehicle is the text structure proposed by Meteer. Following Panaget, we also distinguish between the ideational and the textual semantic categories, and use the upper model to replace the former. Based on this, a further extension is made to support aggregation before realization decisions are made. While our the framework of our macroplanner is kept language independent, our microplanner draws on language specific linguistic sources such as realization classes and lexicon. Since English and German are the first two languages to be generated and because the sublanguage of our mathematical domain is relatively limited, the upper model and the textual semantic categories are designed to cope with both languages. Since the work reported is still in progress, we also discuss open problems we are facing. 1 Introduction Most current na...

The capabilities of a automated theorem prover's interface are essential for the effective use of (interactive) proof systems.

This is an extended abstract of a talk to be presented at the Future Issues for Multilingual Text Processing workshop of PRICAI-96. This talk intends to give an overview of the project ACNLG (Applied Chinese Natural Language Generation) as it currently stands. Since we are at the beginning of our project, the discussion has a corresponding preliminary character. By discussing our philosophy and our approach towards applied multilingual generation (MLG), we hope to stimulate discussions on applicationoriented architectures for MLG. We will go through techniques used in various processing stages and examine the multilingual aspect. We discuss these issues from the point of view of linguistics as well as from that of software engineering. Based on the discussion, we present an architecture we propose for the project ACNLG . 1 Overview of ACNLG ACNLG (Applied Chinese Natural Language Generation) is organized as a cooperation between the German Research Center for Artificial Intelligence (...