An Architecture for Opportunistic Text Generation

We describe the architecture of the ILEX system, • which supports opportunistic text generation. In • web-based text generation, the SYstem cannot plan the entire multi-page discourse because the user's browsing path is unpredictable. For this reason, • the system must be ready opportunistically to take • advantage of whatever path the user chooses. We describe both the nature of opportunism in ILEX's museum domain, and then show how ILEX has been designed to function in this environment. The architecture presented addresses opportunism in both content determination and sentenceplanning. 1 E x p l o i t i n g o p p o r t u n i t i e s in t e x t g e n e r a t i o n • Many models of text generation make use of standard patterns (whether expressed as schemas (e.g. [McKeown 85]) or plan operators (e.g. [Moore and Paris 93])) to break down communicative goals in such a way as to produce extended texts. Such models are making two basic assumptions: 1. Text generation is goal directed, in the sense that spans and subspans of text are designed to achieve unitary communicative goals [Grosz and Sidner 86]. 2. Although the details Of the structUre of a text may have to be tuned to particulars of the communicative situation, generally the structure is determined by the goals and their decomposition. That is, a generator •needs strategies for decomposing the achievement of complex • goals into sequences of utterances, rather than ways of combining sequences of utterances into more complex structures. Generation is "top-down", rather than"bottom-up" [Marcu 97]. Our belief is that there is an important class of NLG problems for which these basic assumptions• are not helpful. These problems all involve situations where semi-fixed explanation strategies are less useful than the ability to exploit opportunities. WordNet gives the following definition of 0pportunity': O p p o r t u n i t y : "A possibility due to a favorable combination of circumstances" Because • opportunities involve •combinations of circumstances, they are often unexpected and hard to predict. It may be too expensive or impossible to have complete knowledge about them. Topdown generation strategies may not be able •to exploit opportunities (except at the cost of looking for all opportunities at all• points) because it is difficult to associate classes of opportunities with fixed stages in the explanation •process. We are investigating opportunistic text generation in the Intelligent Labelling Explorer (ILEX) project, which seeks automatically to generate a sequence of commentaries for items in an electronic 180 South Bridge, Edinburgh EH1 1HN, Email: {chrism,miCko}@dai.ecl.ac.uk. 2 Buccleuch Place, Edinburgh EH8 9LW, Email: {alik, jon}@cogsci.ed, ac.uk