Next: Opportunities: evidence and Up: An Architecture for Opportunistic Previous: An Architecture for Opportunistic

Exploiting opportunities in text generation

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:

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].
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 ``opportunity'':

Opportunity: ``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. Top-down 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 catalogue (or museum gallery) in such a way as to reflect the interest of the user and also to further certain educational (or other) aims. The current domain of the system is the 20th Century Jewellery Exhibit in the Royal Museum of Scotland. However, ILEX is designed to work with any domain where object descriptions are required. The key features of the ILEX application are:

The system has an agenda of communicative goals to achieve, which reflect the goals of the curators.
The user has the freedom to look at any object in the gallery at any time.
The system produces a description of each object asked for by the user, such that:
- each description contributes as best it can to the system's goals;
- the sequence of descriptions fits together into a coherent whole.

The result is a variety of mixed-initiative dialogue:

the user is in control of the high-level communicative goal (what gets described);
the system is in control of how the goal is realised (how the chosen object is described).

In such a dynamically unfolding environment, it is not possible to predict all possible paths through the interaction. The system must thus be ready to exploit opportunities in order to achieve its goals. In ILEX, the user's arbitrary choice represents a horizon beyond which is it not practical to predict. Each generated page may be the last one to be generated and therefore has to be planned to achieve as much as possible on its own. Moreover, almost any part of the generated text can be optimised to exploit the arbitrary situation that the user has got themself into.

Next: Opportunities: evidence and Up: An Architecture for Opportunistic Previous: An Architecture for Opportunistic

Mick O'Donnell
Mon Feb 9 14:09:51 GMT 1998