Maria Milosavljevic

Augmenting the User's Knowledge via Comparison

The process of learning is an incremental exploration of a domain; we do not learn the concepts in a domain in an isolated manner, but instead augment our existing knowledge with new concepts. Consequently, when teaching a new concept to a student, her existing knowledge should be employed in a way which facilitates the process of learning. In describing a new concept to a hearer, it is often beneficial to compare the concept to other concepts with which the hearer is familiar. In particular, comparisons are often used in descriptions in order to reduce the cognitive load on the hearer. This paper outlines three types of comparison found in encyclopaedia descriptions, and describes how a model of the user’s knowledge can be employed to produce descriptions which introduce new concepts by comparison, thus grounding descriptions in the hearer’s existing knowledge. The results are illustrated in the peba-ii natural language generation system.

Dynamic hypertext catalogues: helping users to help themselves

Electronic hypertext catalogues provide an important channel for information provision. However, static hypertext documents cannot be dynamically adapted to help the user find what he/she is looking for. We demonstrate that natural language generation techniques can be used to produce tailored hypertext documents, and we focus on two key benefits of the resulting DYNAMIC HYPERTEXT. First, documents can be tailored more precisely to an individual’s needs and background, thus aiding the search process. Secondly, the incorporation of techniques for comparing catalogue items allows the user to search still more effectively. We describe the automatic generation of hypertext documents containing comparisons, with illustrations from two implemented systems.

Integrating natural language generation and hypertext to produce dynamic documents

Abstract We discuss a task requiring the coherent presentation of heterogeneous information about objects recorded in electronic catalogues. We consider the advantages of combining hypermedia delivery with natural language generation technology, so as to allow us to view a session with such a system as a coherent conversation or dialogue. We describe two prototype systems we have built which make use of these combined techniques, and focus on those aspects of the systems which attempt to provide coherence. Although the techniques themselves are not novel, their combination is relatively recent, and promises to help forge useful tools for accomplishing our specific information retrieval task.

Dynamic document delivery: generating natural language texts on demand

Research in natural language generation promises significant advances in the ways in which we can make available the contents of underlying information sources. Most work in the field relies on the existence of carefully constructed artificial intelligence knowledge bases; however the reality is that most information currently stored on computers is not represented in this format. We describe some work in progress where we attempt to generate large numbers of texts automatically from existing underlying databases. We focus in particular on the automatic generation of descriptions of objects stored in a museum database, highlighting the difficulties that arise in using a real data source, and pointing to some possible solutions.

Automating Financial Surveillance

Financial surveillance technology alerts analysts to suspicious trading events. Our aim is to identify explainable false positives (e.g., caused by price-sensitive information in company news) and explainable true positives (e.g., caused by ramping in forums) by aligning these alerts with publicly available information. Our system aligns 99% of alerts, which will speed the analysts’ task by helping them to eliminate false positives and gather evidence for true positives more rapidly.

Dynamic catalogues on the WWW

Abstract Electronic catalogues are here to stay; however, static WWW documents will not aid the user in finding what she is looking for. We argue for the use of natural language generation techniques to dynamically produce hypertext documents on the WWW, resulting in what we call DYNAMIC HYPERTEXT. A dynamic hypertext document can be tailored more precisely to a particular users needs and backgroud, thus helping the user to search more effectively. We describe the automatic generation of WWW documents and illustrate with two implemented systems.

Customised information delivery: a SIGIR 99 workshop

A major strength of electronic information is the fact that as opposed to its paper counterpart, it can be dynamically modified and tailored to a users need. The problem has been tackled from different angles by different communities. The IR community has revisited its traditional model of query/answers, and now allows for user interaction, synthesized answers, contextual information when presenting answers, etc. The language technology community has designed user models and natural language interfaces to allow better communication and understanding between the system and the user. The Web community has taken a pragmatic approach, with scripts and virtual documents to produce Web pages.