Content Determination

ILEX plans a single page of text, describing a single entity, at a time. The text potential represents the information we can express, and the interconnectivity of information. When we receive the resquest for an entity description, the planner sets that entity as the global focus of the current page. Opportunistic planning then commences. The facts directly connected to that entity represent opportunities: the system can coherently include these facts in the text. If any of these facts are actually selected, then new opportunities are created in two ways:

• Entity-based moves: From the fact, we go to the argument which we didn't enter the fact from. We then select a new fact reachable from this node. See Figure 3. If we followed the Arg2 role of a fact, then we are in a sense selecting a new focus (local focus). The facts we generate about this entity should have the new entity as the focus. Thus in the example, King becomes the Theme of the second sentence. Sentences introduced using entity-based moves can be realised using an Elaboration relation to the starting fact.

  An entity-based move from an individual entity to its generic class entity can be made once the appropriate ``isa'' fact has been selected:

  This item is an organic jewel.
  Organic jewels tend to be ...
  

   

   

  
  : An Entity-Based Move
  

• Relation-based moves: from the initial fact, we follow a relation-node to some new fact. The new fact will be realised textually as a satellite to the original fact's nucleus. The type of the relation-node will determine the rhetorical relation of the link. See Figure 4.

   

   

  
  : A Relation-Based Move
  

Once we select a new fact in either of the ways described above, the new fact may act as the starting point for new opportunistic expansion. Alternatively, we may decide to backtrack to some earlier point, effecting a focus pop in Grosz and Sidner's [Grosz and Sidner 86] terms.

The selection of which opportunity to explore is determined by a number of heuristic factors. Firstly, facts are weighted according to the chain of relations back to the focus of the page [O'Donnell 97]. This is a way of preventing lengthly digressions from the supposed topic of the text. Secondly, each fact is associated with numbers which represent the opportunity `value' of the fact. The opportunities are of two kinds:

Interest.

the estimated value of the fact to the user, e.g. being made of plastic or paper are more interesting ( to the user), because they are unusual in jewellery. Canned anecdotes about a piece of jewellery may also have high interest values.

Importance.

the value of the fact as regards the system's educational agenda, e.g., the system considers it important to educate on stylistic development, so facts about styles are rated highly.

Assimilation.

the degree to which the fact is assumed known to the user, either from general knowledge, or through prior mentions in the web interaction (these values change dynamically).

These three values, interest, importance and assimilation are taken together to calculate the opportunity value of each fact, which is used together with the evaluation of the chain of relations to select which textual opportunities to follow. We have no special theory about where interest and importance come from, though the above examples suggest that there may be domain- and user-type-specific rules that can be used to derive some of them.

In summary, content-determination in ILEX is seen as the task of optimising the selection of opportunities that are offered by the topic of the text, subject to not moving too far from that topic. The result of content-determination is a connected subgraph of the text potential (Figure 5). The use of interest and importance in ILEX is analogous to the use of ``salience'' in [McDonald and Conklin 82]. Because the process is seen as a graph traversal problem, there are also similarities with work on generating text from semantic networks [Simmons and Slocum 72,Sibun 92]. In a sense, our work aims to combine the best of both.

  
Figure 5: Result of Content Determination