Concept Extraction Research Articles

An Analytical Approach to Concept Extraction in HTML Environments

The core of the Internet and World Wide Web revolution comes from their capacity to efficiently share the huge quantity of data, but the rapid and chaotic growth of the Net has extremely complicate...

Context-based ontology building support in clinical domains using formal concept analysis

Objective: Ontology in clinical domains is becoming a core research field in the realm of medical informatics. The objective of this study is to explore the potential role of formal concept analysis (FCA) in a context-based ontology building support in a clinical domain (e.g. cardiovascular medicine here). Methodology: We developed an ontology building support system that integrated an FCA module with a natural language processing (NLP) module. The user interface of the system was developed as a Protégé-2000 JAVA tab plug-in. A collection of 368 textual discharge summaries and a standard dictionary of Japanese diagnostic terms (MEDIS ver2.0) were used as the main knowledge sources. A preliminary evaluation was taken to show the usefulness of the system. Results: Stability was shown on the MEDIS-based medical concept extraction with high precision. 73±14% (mean±S.D.) of the compound medical phrases extracted were sufficiently meaningful to form a medical concept from a clinical perspective. Also, 57.7% of attribute implication pairs (i.e. medical concept pairs) extracted were identified as positive from a clinical perspective. Conclusion: Under the framework of our ontology building support system using FCA, the clinical experts could reach a mass of both linguistic information and context-based knowledge that was demonstrated as useful to support their ontology building tasks.

Automatic concept extraction from spoken medical reports

Objective: The objective of this project is to investigate methods whereby a combination of speech recognition and automated indexing methods substitute for current transcription and indexing practices. Methods: We based our study on existing speech recognition software programs and on nomindex, a tool that extracts MeSH concepts from medical text in natural language and that is mainly based on a French medical lexicon and on the UMLS. For each document, the process consists of three steps: (1) dictation and digital audio recording, (2) speech recognition, (3) automatic indexing. The evaluation consisted of a comparison between the set of concepts extracted by nomindex after the speech recognition phase and the set of keywords manually extracted from the initial document. The method was evaluated on a set of 28 patient discharge summaries extracted from the MENELAS corpus in French, corresponding to in-patients admitted for coronarography. Results: The overall precision was 73% and the overall recall was 90%. Indexing errors were mainly due to word sense ambiguity and abbreviations. A specific issue was the fact that the standard French translation of MeSH terms lacks diacritics. A preliminary evaluation of speech recognition tools showed that the rate of accurate recognition was higher than 98%. Only 3% of the indexing errors were generated by inadequate speech recognition. Discussion: We discuss several areas to focus on to improve this prototype. However, the very low rate of indexing errors due to speech recognition errors highlights the potential benefits of combining speech recognition techniques and automatic indexing.

Clustering revealed in high‐resolution simulations and visualization of multi‐resolution features in fluid–particle models

AbstractSimulating natural phenomena at greater accuracy results in an explosive growth of data. Large‐scale simulations with particles currently involve ensembles consisting of between 106 and 109 particles, which cover 105–106 time steps. Thus, the data files produced in a single run can reach from tens of gigabytes to hundreds of terabytes. This data bank allows one to reconstruct the spatio‐temporal evolution of both the particle system as a whole and each particle separately. Realistically, for one to look at a large data set at full resolution at all times is not possible and, in fact, not necessary. We have developed an agglomerative clustering technique, based on the concept of a mutual nearest neighbor (MNN). This procedure can be easily adapted for efficient visualization of extremely large data sets from simulations with particles at various resolution levels. We present the parallel algorithm for MNN clustering and its timings on the IBM SP and SGI/Origin 3800 multiprocessor systems for up to 16 million fluid particles. The high efficiency obtained is mainly due to the similarity in the algorithmic structure of MNN clustering and particle methods. We show various examples drawn from MNN applications in visualization and analysis of the order of a few hundred gigabytes of data from discrete particle simulations, using dissipative particle dynamics and fluid particle models. Because data clustering is the first step in this concept extraction procedure, we may employ this clustering procedure to many other fields such as data mining, earthquake events and stellar populations in nebula clusters. Copyright © 2003 John Wiley & Sons, Ltd.

An effective concept extraction method for improving text classification performance

This paper presents a new way to extract concept that can be used to improve text classification performance (precision and recall). The computational measure will be divided into two layers. The bottom layer called document layer is concerned with extracting the concepts of particular document and the upper layer called category layer is with finding the description and subject concepts of particular category. The relevant implementation algorithm that dramatically decreases the search space is discussed in detail. The experiment based on real-world data collected from Infor-Bank shows that the approach is superior to the traditional ones.

The Interspace: concept navigation across distributed communities

Within the next decade, computing technology will transform the Internet into the Interspace, an information infrastructure that supports semantic indexing and concept navigation across widely distributed community repositories. With the Interspace, the global information infrastructure will, for the first time, directly support interaction with abstraction. This infrastructure uses technologies that go beyond searching individual repositories to analyze and correlate knowledge across multiple sources and subjects. The Interspace will offer distributed services to transfer concepts across domains, just as Arpanet used distributed services to transfer files across machines and the Internet uses distributed services to transfer objects across repositories. The Community Architectures for Network Information Systems Laboratory has developed a working Interspace prototype that uses scalable technologies for concept extraction and navigation. They have successfully tested these technologies, which compute contextual frequency of document phrases within a community repository, on discipline-scale, real-world collections.

Understanding the pathogenesis of autoimmune hepatitis.

The aim of this study was to review the pathogenic mechanisms of autoimmune hepatitis, identify gaps in knowledge, and focus future investigative efforts. The study was based on a review of all relevant articles on the mechanisms of autoimmunity in autoimmune liver disease from 1980 to 2000, extraction of pertinent concepts from the medical literature; and integration of evolving paradigms of pathogenesis with personal experiences and investigations. Autoimmune hepatitis is a consequence of autoantigen exposure, genetic predisposition, and defective immunoregulatory mechanisms. Autoantigen is optimally presented by class II molecules of the major histocompatibility complex that have lysine residues at position DRbeta71 of the antigen-binding groove. Cytokines and non-disease-specific autoimmune promoters modulate immune reactivity. Cell-mediated and antibody-dependent mechanisms contribute to hepatocyte injury. Multiple disturbances in the homeostatic mechanisms that preserve self-tolerance are likely in autoimmune hepatitis. Future investigations must focus on individual determinants of autoantigen presentation, immunocyte activation, and liver cell destruction. Findings can then be integrated into a comprehensive knowledge base that may be applicable to other autoimmune diseases.

Identifying Temporal Components in a Chinese Temporal Information System

Temporal structures are important semantic carriers in information extraction. Over the past few years, temporal information processing and temporal database management have gradually become popular research topics. Unfortunately, few researchers have investigated these areas in Chinese. This impels us to put efforts on exploiting Chinese temporal expressions for concept-based reasoning. The lack of regular morphological tense markers makes Chinese temporal expressions complicated. Therefore, the study of Chinese temporal information (or concept) extraction has profound significance. In this paper, an algorithm for Chinese temporal information extraction is presented. We argue that the type of Chinese concept, which is embedded in a sentence, must first be identified by verb properties. Thereafter, the overall temporal concept can be determined when the other temporal and non-temporal components in the sentence are considered. Based on the investigation of Chinese temporal expressions, we then propose a heuristic algorithm to identify temporal components from the running text. The performance of the algorithm in terms of recall and precision is reported. The algorithm was proved successful in the test. It is worth noting that the work presented in this paper is only a part of an ongoing project, which aims at extracting and evaluating temporal relations over Hong Kong financial news reports.

Combining Conceptual Clustering and Principal Component Analysis for State Space Based Process Monitoring

Multivariate statistics and unsupervised machine learning have recently been studied by many researchers for process monitoring and fault diagnosis. These approaches often depend on calculating a similarity or distance measure to group data sets into clusters. Apart from giving predictions, they are not able to give causal explanations on why a specific set of data is assigned to a particular cluster. In this work, a conceptual clustering approach is presented for designing state space based monitoring systems, which is able to generate conceptual knowledge on the major variables which are responsible for clustering, as well as projecting the operation to a specific operational state. A critical issue in this approach is how to conceptually represent dynamic trend signals. For this purpose, principal component analysis is used for concept extraction from real-time dynamic trend signals. The method is introduced using a continuous stirred tank reactor as a case study. Application of the approach to a refinery methyl tert-butyl ether process is also presented.

Automated Semantic Indexing of Imaging Reports to Support Retrieval of Medical Images in the Multimedia Electronic Medical Record

This paper describes preliminary work evaluating automated semantic indexing of radiology imaging reports to represent images stored in the Image Engine multimedia medical record system at the University of Pittsburgh Medical Center. The authors used the SAPHIRE indexing system to automatically identify important biomedical concepts within radiology reports and represent these concepts with terms from the 1998 edition of the U.S. National Library of Medicine's Unified Medical Language System (UMLS) Metathesaurus. This automated UMLS indexing was then compared with manual UMLS indexing of the same reports. Human indexing identified appropriate UMLS Metathesaurus descriptors for 81% of the important biomedical concepts contained in the report set. SAPHIRE automatically identified UMLS Metathesaurus descriptors for 64% of the important biomedical concepts contained in the report set. The overall conclusions of this pilot study were that the UMLS metathesaurus provided adequate coverage of the majority of the important concepts contained within the radiology report test set and that SAPHIRE could automatically identify and translate almost two thirds of these concepts into appropriate UMLS descriptors. Further work is required to improve both the recall and precision of this automated concept extraction process.

Living with high blood pressure.

This study was undertaken to explore the experience of people taking long-term antihypertensive medication. The study contributes to the understanding health professionals have of people with high blood pressure and the antihypertensive treatments they receive. Consideration was given to the full life context of people taking long-term antihypertensive medication and the health/medical culture in which people find themselves. A qualitative method of inquiry generated the descriptive data. Nineteen participants (four men and 15 women) were interviewed once, of which 16 were interviewed a second time. Data analysis involved extraction of concepts which in turn were clustered into themes. An organizing framework was constructed to integrate the six themes and 18 sub-themes. The framework represents the individual's experience as a sequence, starting broadly in the social context of her/his life, and narrowing down to the particulars of personal routine and patterns referring to living with hypertension and it's medication regimens. The final theme refers to the broader context of the health culture. A vast range of experiences were described by participants taking long-term antihypertensive medication. This accentuates the necessity for health professionals to address the uniqueness of the individual, and consider the context of a person's life when prescribing and monitoring medications for people with high blood pressure.

Dimensionality reduction via discretization

The existence of numeric data and large numbers of records in a database present a challenging task in terms of explicit concepts extraction from the raw data. The paper introduces a method that reduces data vertically and horizontally, keeps the discriminating power of the original data, and paves the way for extracting concepts. The method is based on discretization (vertical reduction) and feature selection (horizontal reduction). The experimental results show that (a) the data can be effectively reduced by the proposed method; (b) the predictive accuracy of a classifier (C4.5) can be improved after data and dimensionality reduction; and (c) the classification rules learned are simpler.

Coding Choices for Textual Analysis: A Comparison of Content Analysis and Map Analysis

Content and map analysis, procedures for coding and understanding texts, are described and contrasted. Where content analysis focuses on the extraction of concepts from texts, map analysis focuses on the extraction of both concepts and the relationships among them. Map analysis thus subsumes content analysis. Coding choices that must be made prior to employing content-analytic procedures are enumerated, as are additional coding choices necessary for employing map-analytic procedures. The discussion focuses on general issues that transcend specific software procedures for coding texts from either a content-analytic or map-analytic perspective.

The Concept and Market Extraction of Effective Age for Residential Properties

This paper presents a theoretical and algebraic technique for the estimation of effective age on a residential property. This estimate for the subject property is a number that is calculated relati...

A conceptual approach to document retrieval

A document retrieval system is a quite useful tool in office environments, expecially for professionals who are interested in keeping along with the state of the art of their field by quickly consulting documents. The paper describes the design and the implementation of a document retrieval system based on a concept extraction from documents. Concept extraction is implemented using an internal knowledge representation (semantic network memory) of the subject the documents deal with retrieving concepts from a text is performed by search/inferential algorithms. Advantages of such methods are shown by comparing it to keyword extraction. The prototype system implementation is described. This system is actually in experimental phase. Several test descriptions provide a sketch of the first results.

A bounded velocity postulate and special relativity

Although the theory of special relativity follows in a straight forward manner from the assumption that the speed of light is invariant as measured by observers having uniform velocities with respect to one another (M. Steib, Extraction of relativistic concepts, Amer. J. Phys. 44(1976), 60-62), it would be interesting to know that the theory also follows from the assumption that there is some number l such that no velocity exceeds l. The article, Einstein: a natural completion of Newton, (J. Math. Anal. Appl. 42(1973), 377-380) outlines a candidate for such a derivation based on a given conjecture. 2 references.

Extraction of relativistic concepts

Two elementary algebra word problems are presented which have answers helpful enough in the derivation of the effects of special relativity that little else need be added in this derivation. The two problems are entirely in the classical setting before any reference is made to relativistic assumptions. The chance for confusion related to relativistic assumption is thus extracted and concentrated into a very short and direct part of the derivations for the contraction of lengths, retardation of time, and nonsynchronization of clocks. Thus these effects of the constancy of the speed of light follow immediately and directly from the assumption of the constancy of this speed in a way which elucidates the logical connection between the assumption and the effects.

Generating and validating RAM requirements : J. Lavery and M. Westmoreland. Proc. 1974 Reliability and Maintainability Symposium, U.S.A. 244 (29–31 Jan. 1974)

Plagiarism is increasingly becoming a major issue in the academic and educational domains. Automated and effective plagiarism detection systems are direly required to curtail this information breach, especially in tackling idea plagiarism. The proposed approach is aimed to detect such plagiarism cases, where the idea of a third party is adopted and presented intelligently so that at the surface level, plagiarism cannot be unmasked. The reported work aims to explore syntax-semantic concept extractions with genetic algorithm in detecting cases of idea plagiarism. The work mainly focuses on idea plagiarism where the source ideas are plagiarized and represented in a summarized form. Plagiarism detection is employed at both the document and passage levels by exploiting the document concepts at various structural levels. Initially, the idea embedded within the given source document is captured using sentence level concept extraction with genetic algorithm. Document level detection is facilitated with word-level concepts where syntactic information is extracted and the non-plagiarized documents are pruned. A combined similarity metric that utilizes the semantic level concept extraction is then employed for passage level detection. The proposed approach is tested on PAN13-141plagiarism corpus for summary obfuscation data, which represents a challenging case of idea plagiarism. The performance of the current approach and its variations are evaluated both at the document and passage levels, using information retrieval and PAN plagiarism measures respectively. The results are also compared against six top ranked plagiarism detection systems submitted as a part of PAN13-14 competition. The results obtained are found to exhibit significant improvement over the compared systems and hence reflects the potency of the proposed syntax-semantic based concept extractions in detecting idea plagiarism.

The Development of a Thai Spoken Dialogue System

This article summarily reports the development of the first Thai spoken dialogue system (SDS), namely a Thai Interactive Hotel Reservation Agent (TIRA) . In the development, a multi-stage technique of spoken language understanding (SLU), which combined a word spotting technique for concept extraction and a pattern classification technique for goal identification, was proposed. To improve system performance, a novel approach of logical n-gram modeling was developed for concept extraction in order to enhance the SLU robustness. Furthermore, dialogue contextual information was used to help understanding and finally, an error detection mechanism was constructed to prevent unreliable interpretation outputs of the SLU. All the mentioned algorithms were incorporated in the TIRA system and evaluated by real users.