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 recent developments in question-answering research and the availability of unparalleled resources developed specifically for automatic semantic processing of text in the medical domain provides a unique opportunity to explore complex question answering in the domain of clinical medicine. This article presents a system designed to satisfy the information needs of physicians practicing evidence-based medicine. We have developed a series of knowledge extractors, which employ a combination of knowledge-based and statistical techniques, for automatically identifying clinically relevant aspects of MEDLINE abstracts. These extracted elements serve as the input to an algorithm that scores the relevance of citations with respect to structured representations of information needs, in accordance with the principles of evidencebased medicine. Starting with an initial list of citations retrieved by PubMed, our system can bring relevant abstracts into higher ranking positions, and from these abstracts generate responses that directly answer physicians ’ questions. We describe three separate evaluations: one focused on the accuracy of the knowledge extractors, one conceptualized as a document reranking task, and finally, an evaluation of answers by two physicians. Experiments on a collection of real-world clinical questions show that our approach significantly outperforms the already competitive PubMed baseline. 1.

We have developed an in6 vative searchin terface that allowsnAOz5z ert users to move through large in97z86 tion spacesin a flexible manle without feelin lost. The design goal was to o#er users a "browsin the shelves" experien5 seamlessly in tegrated with focused search. Key to achievin our goal is the explicit exposure of hierarchical faceted metadatain a manz6 that is in tuitive an in vitin to users. After several iteration of design an testinA the usability results are strikinA] positive. We believe our approach marks a major step forward in search userin terfacesan can serve as a model for web-based collection of up to 100,000 items.

Narrative reports in medical records contain a wealth of information that may augment structured data for managing patient information and predicting trends in diseases. Pertinent negatives are evident in text but are not usually indexed in structured databases. The objective of the study reported here was to test a simple algorithm for determining whether a finding or disease mentioned within narrative medical reports is present or absent. We developed a simple regular expression algorithm called NegEx that implements several phrases indicating negation, filters out sentences containing phrases that falsely appear to be negation phrases, and limits the scope of the negation phrases. We compared NegEx against a baseline algorithm that has a limited set of negation phrases and a simpler notion of scope. In a test of 1235 findings and diseases in 1000 sentences taken from discharge summaries indexed by physicians, NegEx had a specificity of 94.5%(versus 85.3% for the baseline), a positive predictive value of 84.5% (versus 68.4% for the baseline) while maintaining a reasonable sensitivity of 77.8% (versus 88.3% for the baseline). We conclude that with little implementation effort a simple regular expression algorithm for determining whether a finding or disease is absent can identify a large portion of the pertinent negatives from discharge summaries.

In this paper we consider methods for automatic query expansion from top retrieved documents (i.e., retrieval feedback) which make use of various functions for scoring expansion terms within Rocchio’s classical reweighting scheme. An analytical comparison shows that the retrieval performance of methods based on distinct term-scoring functions is comparable on the whole query set but considerably differs on single queries, consistent with the fact that the ordered sets of expansion terms suggested for each query by the different functions are largely uncorrelated. Motivated by these findings, we argue that the results of multiple functions can be merged, by analogy with ensembling classifiers, and present a simple combination technique based on the rank values of the suggested terms. The combined retrieval feedback method is effective not only with respect to unexpanded queries but also to any individual method, with notable improvements on the system’s precision. Furthermore, the combined method is robust with respect to variation of experimental parameters and it is beneficial even when the same information needs are expressed with shorter queries.

Metadata interoperability is a fundamental requirement for access to information within networked knowledge organization systems. The Harmony International Digital Library Project [1] has developed a common underlying data model (the ABC model) to enable the scalable mapping of metadata descriptions across domains and media types. The ABC model, described in [2], provides a set of basic building blocks for metadata modeling and recognizes the importance of 'events ' to unambiguously describe metadata for objects with a complex history. In order to test and evaluate the interoperability capabilities of this model, we applied it to some real multimedia examples and analysed the results of mapping from the ABC model to various different metadata domains using XSLT [3]. This work revealed serious limitations in XSLT's ability to support flexible dynamic semantic mapping. In order to overcome this, we developed MetaNet [4], a metadata term thesaurus which provides the additional semantic knowledge which is non-existent within declarative XML-encoded metadata descriptions. This paper describes MetaNet, its RDF Schema [5] representation and a hybrid mapping approach which combines the structural and syntactic mapping capabilities of XSLT with the semantic knowledge of MetaNet, to enable flexible and dynamic mapping among metadata standards. 1.

A new, fully automated approach for indexing documents is presented based on associating textwords in a training set of bibliographic citations with the indexing of journals. This journal-level indexing is in the form of a consistent, timely set of journal descriptors (JDs) indexing the individual journals themselves. This indexing is maintained in journal records in a serials authority database. The advantage of this novel approach is that the training set does not depend on previous manual indexing of hundreds of thousands of documents (i.e., any such indexing already in the training set is not used), but rather the relatively small intellectual effort of indexing at the journal level, usually a matter of a few thousand unique journals for which retrospective indexing to maintain consistency and currency may be feasible. If successful, JD indexing would provide topical categorization of documents outside the training set, i.e., journal articles, monographs, WEB documents, reports from the grey literature, etc., and therefore be applied in searching. Because JDs are quite general, corresponding to subject domains, their most probable use would be for improving or refining search results.

ABSTRACT: Full-text documents are a vital and rapidly growing part of online biomedical information. A single large document can contain as much information as a small database, but normally lacks the tight structure and consistent indexing of a database. Retrieval systems will often miss highly relevant parts of a document if the document as a whole appears irrelevant. Access to full-text information is further complicated by the need to search separately many disparate information resources. This research explores how these problems can be addressed by the combined use of two techniques: (1) natural language processing for automatic concept-based indexing of full text, and (2) methods for exploiting the structure and hierarchy of full-text documents. We describe methods for applying these techniques to a large collection of fulltext documents drawn from the Health Services/Technology Assessment Text (HSTAT) database at the National Library of Medicine (NLM), and examine how this hierarchical concept indexing can assist both document- and source-level retrieval in the context of NLM’s Information Sources Map project. Wright et al. 2

An experiment was performed at the National Library of Medicine ® (NLM ® ) in word sense disambiguation (WSD) using the Journal Descriptor Indexing (JDI) methodology. The motivation is the need to solve the ambiguity problem confronting NLM’s MetaMap system, which maps free text to terms corresponding to concepts in NLM’s Unified Medical Language System ® (UMLS ® ) Metathesaurus ®. If the text maps to more than one Metathesaurus concept at the same high confidence score, MetaMap has no way of knowing which concept is the correct mapping. We describe the JDI methodology, which is ultimately based on statistical associations between words in a training set of MEDLINE ® citations and a small set of journal descriptors (assigned by humans to journals per se) assumed to be inherited by the citations. JDI is the

Underspecified semantic structures serve as the basis for indexing terms for information retrieval. Biomedical semantic types from the National Library of Medicine’s Unified Medical Language System ® constrain coordinate structures to increase the accuracy of the semantic repre-sentation. Preliminary experiments conducted on 3,000 MEDLINE titles and abstracts indicate that the approach contributes to increased precision. I.