Structured document retrieval aims at retrieving document components that best satisfy a query, instead of merely retrieving predefined document units. This paper reports on an investigation of a idf-acc approach, where tf and idf are the classical term fi'equency and inverse document frequency, and acc, a new parameter called accessibility, that captures the structure of documents. The tf-idf-acc approach is defined using a probabilistic relational algebra. To investigate the retrieval quality and estimate the acc values, we developed a method that automatically constructs diverse test collections of structured documents from a standard test collection, with which experiments were carried out.

Abstract. In this paper, we examine the methodological issues involved in constructing test collections of structured documents and obtaining best entry points for the evaluation of the focussed retrieval of document components. We describe a pilot test of the proposed test collection construction methodology performed on a document collection of Shakespeare plays. In our analysis, we examine the effect of query complexity and type on overall query difficulty, the use of multiple relevance judges for each query, the problem of obtaining exhaustive relevance assessments from participants, and the method of eliciting relevance assessments and best entry points. Our findings indicate that the methodology is indeed feasible in this small-scale context, and merits further investigation. 1

Documents often display a hierarchical structure. For example, a SGML document contains a title, several sections, which themselves contain paragraphs. In this paper, we develop a formal model to represent in a uniform manner structured documents by their content and structure. As a result, querying structured documents can be done with respect to their content, their structure, or both. The model is based on a possible worlds approach, modal operators and uncertainty distributions.

Effective retrieval of structured documents should exploit the content and structural knowledge associated with the documents. This knowledge can be used to focus retrieval to the best entry points: document components that contain relevant information, and from which users can browse to retrieve further relevant components. To enable this, suitable representation methods must be developed. This paper presents a model for representing structured documents to allow for their focussed retrieval. The model is founded on fuzzy aggregation, an approach based on the fuzzy representation of linguistic quantifiers and ordered weighted averaging operators. By defining the representation of a document component as the fuzzy aggregation of its related components, we arrive at a document representation that supports the selection of best entry points. 1

We present a bayesian framework for XML document retrieval. This framework allows us to consider content only and structure and content queries. We perform the retrieval task using inference in our network. Our model can adapt to a specific corpora through parameter learning.

Structured document retrieval requires different user graphical interfaces from

This paper describes the implementation and user-centred evaluation of a prototype interface, the RelevanceLinkBar interface. The results of the evaluation show that the RelevanceLinkBar interface supported users in their browsing behaviour, allowing them to find more relevant documents, and was strongly preferred over a standard results interface

Many document collections contain documents that have significant structure. Structured document retrieval requires different models and interfaces from standard Information Retrieval. An Information Retrieval system dealing with structured documents has to enable a user to query, browse retrieved documents, and provide query refinement and relevance feedback based not only on full documents but also on specific parts of them, according to their structure. Currently, very few IR systems enable such level of flexibility and interaction, because of limitations in indexing and retrieval models and in interfaces. In this paper, we present the design of a new graphical user interface for structured document retrieval. This interface provides the user with an intuitive and yet powerful set of tools for structured document searching, retrieved list navigation, and search refinement. 1

Structured documents are composed of objects with a content and a logical structure. The effective retrieval of structured documents requires models that provide for a content-based retrieval of objects that takes into account their logical structure, so that the relevance of an object is not solely based on its content, but also on the logical structure among objects.

MPEG-7 is an emerging standard for representing information carried by multimedia data. Such a standard is considered to be crucial for the oncoming integration of broadcast (TV) and Internet technologies and applications. This paper reports on the development of methods for searching multimedia data using MPEG-7 in the context of a broadcast application, and, in particular, in the development of a broadcast terminal with interactive functions. The paper provides an introduction to MPEG-7, a description of a retrieval model for MPEG-7, and the description of a prototypical user interface implemented for demonstrating the terminal. MPEG-7 was examined to determine the MPEG-7 parts necessary to implement a search component in a broadcast terminal. The retrieval model was developed and implemented using the HySpiritfi software development kit, which is a flexible framework for representing complex data and describing retrieval functions effectively. The user interface provides insights in integrating a search functionality in a broadcast terminal. 1.