Title:Dynamic Generation of Museum Web Pages: The Intelligent Labelling Explorer
Authors:Janet Hitzeman, Jon Oberlander
Publication:MW97: Museums and the Web 1997

The first phase of the Intelligent Labelling Explorer project has built the ILEX-1 system, which uses Natural Language technology to generate descriptions of objects displayed in a museum gallery. Each description appears on a Web page, and the user can move from page to page, viewing the objects in any order, mimicking the experience of someone walking through the museum. Crucially, these descriptions aren't simply retrieved from a storage space, but are generated on demand by combining canned text with fully generated text in a coherent way. This use of "dynamic hypertext" allows ILEX-1 to generate descriptions appropriate to the expertise level of the user and, for instance, to refer back to objects the user has already seen or to suggest objects the user might be interested in based on what objects they've chosen to look at so far. For example, ILEX-1 can refer to previously seen objects as in "Like the brooch you just saw, these earrings were designed by Jesse M. King or "Other jewels in the Bohemian style include a necklace designed for Liberty & Co. and a ring made out of glass." To date, two versions have been implemented (ILEX-0 and ILEX-1); both describe objects in the National Museums of Scotland's 20th Century Jewelry Gallery. One of the central concerns of ILEX-1 is to ensure that the descriptions generated are coherent, and this paper will describe the module for choosing the appropriate noun phrase to use at a particular place in the text. This module takes into account the user's familiarity with the objects described based on expertise level and user history, and must take into account linguistic information such as the structure of the text.