This paper introduces a novel user interface that integrates search and browsing of very large category hierarchies with their associated text collections. A key component is the separate but simultaneous display of the representations of the categories and the retrieved documents. Another key component is the display ofmultiple selected categories simultaneously, complete with their hierarchical context. The prototype implementation uses animation and a three-dimensional graphical workspace to accommodate the category hierarchy and to store intermediate search results. Query specification in this 3D environment is accomplished via a novel method for painting Boolean queries over a combination of category labels and free text. Examples are shown on a collection of medical text.

The combination of different text representations and search strategies has become a standard technique for improving the effectiveness of information retrieval. Combination, for example, has been studied extensively in the TREC evaluations and is the basis of the “meta-search” engines used on the Web. This paper examines the development of this technique, including both experimental results and the retrieval models that have been proposed as formal frameworks for combination. We show that combining approaches for information retrieval can be modeled as combining the outputs of multiple classifiers based on one or more representations, and that this simple model can provide explanations for many of the experimental results. We also show that this view of combination is very similar to the inference net model, and that a new approach to retrieval based on language models supports combination and can be integrated with the inference net model.

Semantic metadata describing subject content plays a vital role in supporting indexing and retrieval in Digital Libraries. Mechanisms used to deliver this metadata include keyword collections, thesauri and classi®cations. Constructing a large thesaurus, however, is a di cult process which can be facilitated through the application of knowledge representation techniques developed for managing and reasoning about concepts. We describe such a scheme ± a Description Logic �DL) ± and show through an example how a DL can playa part in the classi®cation construction process, aiding in the production of coherent hierarchies and ensuring that the relationships represented in a thesaurus

by Vivien Petras

Abstract-An intermediary expert system (IES) helps both end users and professional searchers to conduct their online database searching. To provide advice about term selec-tion and query expansion, an IES should include a terminological knowledge structure. Terminological attributes as well as other properties could provide the starting point for building a knowledge base, and knowledge acquisition could rely on knowledge-base techniques coupled with statistical techniques. The searching behavior of expert online searchers would provide one source of knowledge. The knowledge structure would include three constructs for each term: frequency data, a hedge, and a position in a classification scheme. Switching vocabularies or languages could provide a meta-schema and facilitate the interoperability of databases in similar subject domains. To develop such knowledge structure, future research should focus on terminological attributes, word and phrase disambiguation, automated text processing, and the role of thesauri and clas-sification schemes in indexing and retrieval. In particular, such research should develop techniques that combine knowledge-base and statistical methods and that consider user preferences. 1.

The CODER (COmposite Document Expert/extended/effective Retrieval) project is an investigation of the applicability of artificial intelligence techniques to the information retrieval task of analyzing, storing, and retrieving heterogeneous collections of “composite documents.” In order to support some of the processing desired, and to allow experimentation in information retrieval and natural language processing, a lexicon was constructed from the machine readable Collins Dictionary of the English Language. After giving background, motivation, and a survey of related work, the Collins lexicon is discussed. Following is a description of the conversion process, the format of the resulting Prolog database, and characteristics of the dictionary and relations. To illustrate what is present and to explain how it relates to the files produced from Webster's Seventh New Collegiate Dictionary, a number of comparative charts are given. Finally, a grammar for adverb definitions is presented, together with a description of defining formula that usually indicate the type of the adverb. Ultimately it is hoped that definitions for adverbs and other words will be parsed so that the relational lexicon being constructed will include many additional relationships and other knowledge about words and their usage.

Abstract not found

We address some issues relating to retrieval from unfamiliar text collections consisting of full-length documents. We claim that displaying query results in terms of inter-document similarity is inappropriate with long texts, and suggest instead that the results of simple initial queries should be contextualized according to category sets that correspond to the main topics of the texts. We argue that main topics of long texts should be represented by multiple categories, since in most cases one category cannot adequately classify a text. We describe a new automatic categorization algorithm that does not require pre-labeled texts and a prototype browsing interface that presents a simple mechanism for displaying multi-dimensional information. 1

Abstract. Searching specialized collections, such as biomedical literature, typically requires intimate knowledge of a specialized terminology. Hence, it can be a disappointing experience: not knowing the right terms to use and being unaware of synonyms or variations in terminology might result in low recall scores. We study the role of a thesaurus in the biomedical information retrieval process. We start by giving a description of vocabulary mismatch problems between natural language queries and relevant documents in biomedical literature search; we provide a detailed case study and observe the impact of vocabulary mismatch problems on retrieval effectiveness. Additionally, we analyze the associated MeSH thesaurus terms used to index the documents in the collection. Based on our observations, we propose a method for exploiting the MeSH thesaurus to improve retrieval effectiveness and, more specifically, to increase recall. We carry out a series of thesaurus-based retrieval experiments that show substantial performance improvements. We conclude with a detailed analysis of the retrieval results. 1

The introduction of computerized post-coordination has solved many of the problems of pre-coordinated subject access. However, the adoption of computerized post-coordination results in the loss of some pre-coordination benefits. Specifically, the effect of hiding terms within the context of others is lost in post-coordination which gives lead status to every document term, This results in spurious matches of terms out of context. Library patrons and Internet searchers are increasingly dissatisfied with subject access performance, in part because of unmanageably large retrieval sets. The need to enhance precision and limit the size of retrieval sets motivates this work which proposes partial coordination, an approach which incorporates the advantages of computer search with the ability of pre-coordination to limit spurious partial matches and thereby enhance precision.