The Use of Summaries in XML Retrieval

Summarisation of the logical structure of XML documents

“…is it sections and sub-sections to be included or sections only, etc.) has been found to be unsatisfactory in user studies carried out as part of the INEX Interactive Track (Malik, Larsen, & Tombros, 2007), in the context of XML retrieval (Szlávik, 2006b). We also found in our study that a ToC should reflect the user's query and that it is not enough to determine ToC-worthiness only based on type (e.g.…”

“…However, we have shown in previous work that some portions of documents might be more important to a user, and thus, these portions should be made more prominent in the table of contents (Szlávik, 2006b). For example, for some sections, we might need to include paragraphs in the corresponding ToC, while other sections (being unimportant or not relevant) might be completely omitted from it.…”

Learning-based summarisation of XML documents

“…One direction to follow, would be to conduct a user study in which to observe what kinds of XML elements searchers would prefer to see in a summarised version after the initial retrieval. Some initial investigation can be found in Szlavik et al (2006aSzlavik et al ( , 2006b, where results indicate a positive correlation between element probability of relevance, length and user preference to see summary information. Further research in this direction is currently underway.…”

“…Essentially, they can be applied to any XML element that can be meaningfully summarised, i.e. that is informative and long enough to make its summarisation meaningful (Szlavik et al, 2006b). In particular, the most effective content (expanded concepts with word clusters and projected concepts on word clusters), and structure features (depth of element and position of paragraph in the element), can be applied to various granularity levels within an XML tree.…”

“…In this way, summaries can also be associated with the other elements forming the document, in addition to the retrieved elements themselves (Szlavik et al, 2006a). The choice of the "meaningful" granularity of elements to be summarised is also currently being investigated (Szlavik et al, 2006b), as some retrieved elements may simply be too short to be summarised. The summarisation of XML documents is also beginning to draw attention from researchers (Alam et al, 2003;Litkowski, 2003;Sengupta et al, 2004;Szlavik et al, 2006a).…”