Semi-structured Text Research Articles

A rule-based transformation system for converting semi-structured medical documents

The electronic health record (EHR) enabled the cost-efficient handling and processing of health information. By storing medical documents in digitized form, the EHR ensures the fast and reliable availability of health information. However, as not all health care providers use the same EHR format and health document structures, the efficiency of the data sharing process is severely reduced. In this paper we present a rule-based transformation system that converts semi-structured (annotated) text into standardized formats, such as HL7 CDA. Our approach identifies relevant information in the input document by analyzing its structure as well as its content and inserts the required elements into corresponding reusable CDA templates, where the templates are selected according to the CDA document type-specific requirements. The research results enable the efficient transformation of various EHR structures into a standardized format and therefore contribute to increasing the data sharing efficiency across health care providers.

Special issue on critical considerations around eInnovations in health

Today, it is indeed the best of times and the worst of times when it comes to healthcare delivery. On one hand healthcare globally is facing tremendous challenges to provide effective, efficient, efficacious patient centric care and on the other hand we are witnessing the most intense period of e-health solution development yet which holds the promise of realising a superior state for healthcare delivery. At such a time there are clearly several considerations that must be considered regarding the technology innovations in healthcare , or as we have coined the term eInnovations in health. In an attempt to highlight such key issues and developments we have compiled the following special issue. It was never our goal to provide an exhaustive list of topics but rather a pot-pourri of topics that focus on important aspects of eInnovations in health that will help to stimulate further debate and engage more research in this vital area. The eight papers that make up this special issue include: “Evaluation of Microsoft HealthVault and Google Health Personal Health Records” by Ali Sunyaev This paper examines and compares the design of application programming interfaces of two personal health record systems. “Tailoring Software Process Capability/ Maturity Models for the Health Domain” by von Wangenheim et al. which examines web-based asynchronous store and forward telemedicine systems for diagnostic purposes. “The Influence of EHR Components on Admission Decisions” by Assuli et al. which looks at an ED environment to assess the specific data components that improve the process of decision making with regard to electronic health record design. “Toward a Typology of Health 2.0 Collaboration Platforms and Websites” Kordzadeh and Warren This paper develops a typology for Health 2.0 collaboration platforms and websites and examines these keeping in mind the 2 major actors: the providers and the consumers “A Rule-Based Transformation System for Converting Semi-Structured Medical Documents” by Heurix et al. which focuses on the design and development of a rule based transformation system that converts semi-structured texts into standardised formats. “Some promising areas for IS research in the hospital industry: implications from a case study of operating room scheduling” by He et al. which serves to examine issues with operating room scheduling at a surgery department in the Midwest , US. “A Phased Approach to Implementing Radio Frequency Identification Technologies within the Perioperative Process” by Ryan et al. which looks at the critical considerations and technology issues relating to implementing RFID technology into a hospital context. And finally “Designing Healthy Living Support; Mobile applications added to hybrid (e)Coach Solution” by Simons et al. We hope our readers enjoy this special issue and it serves to stimulate and foster more research in this growing and key area. The Special Issue editors Doug and Nilmini Feb 2013 D. Vogel Information Systems Department, City University of Hong Kong, 83 Tat Chee Avenue, Kowloon Tong, Hong Kong e-mail: isdoug@cityu.deu.hk

The Research of Self-Organizing Maps Based on Document Collections

Web text mining is a new issue in the knowledge discovery research field. It is aimed to help people discover knowledge from large quantities of semi-structured or unstructured text in the web. Several approaches, including some pure and hybrid information retrieval (IR) methods, have been proposed to tackle such an issue. Among these approaches, combining the Self-Organizing Map (SOM) method with the principles of the vector-space model, appears to be a promising alternative for the traditional purely IR-based methods in this problem domain. The encoded documents are organized on another self-organizing map, a document map, on which nearby locations contain similar documents. Special consideration is given to the computation of very large document maps which is possible with general-purpose computers if the dimensionality of the word category histograms is first reduced with a random mapping method and if computationally efficient algorithms are used in computing the SOMs.

Parser Combinators for Parsing Semi-Structured Texts

Parser Combinators for Parsing Semi-Structured Texts

Developing foreign language skills, competence and identity through a collaborative creative writing project

This study examined the effects of a collaborative creative writing project on identity formation and overall language proficiency development among advanced Hebrew students. In an exercise called ‘The Zoning Committee’, college students created the fictional Israeli-American town of Beit Shemesh, located in northern Michigan. Qualitative data collection methods consisting of semi-structured group interviews, observation and text analysis of story drafts showed that the writing project gave students an opportunity to explore significant issues about the Jewish community and their personal lives as manifested in themes and motifs in their fiction. In addition to the social and intrapersonal benefits, the project was beneficial to language proficiency development: it increased confidence and classroom morale, required strategy use, improved writing level and honed listening and speaking skills.

Remembering differently: Use of memory strategies among net-generation ESL learners

Net-generation learners are growing up in an era when much of the learning, communication, socializing and ways of working take place through digital means. Living in this digital era may result in different ways of thinking, ways of approaching learning, strategies, and priorities. The Net-Geners therefore, need new skills and new strategies to perform successfully as learners and workers. This study used a mixed-methods approach to identify whether one such strategy, that is, memorization strategy may have changed for the Net-Generation language learners. The researchers, first obtained quantitative data from 107 ESL tertiary language learners about their strategy use based on Oxford’s (1989) widely used Strategy Inventory for Language Learning (SILL), currently considered the most comprehensive inventory. Data on strategy use was then procured using qualitative methods such as semi-structured interviews, Open-ended questionnaires, and texts of the respondents’ online interaction in a language task. This latter set of data was analysed (i) to compare the qualitative data with the SILL data, and (ii) to identify possible emergent memory strategies among Net-Geners. The study found that memory strategies have not faded from repertoire of strategies for Net-Genres language learners, rather a set of modifications have emerged in terms of storage place, methods of storing information, retrieval system, and use of memory strategies for successful language learning. Key words: Net-Geners, trends, memory, language learning strategies.

Automated Metadata Creation to Enhance Search Capabilities in GPO's Federal Digital System

GPO's Federal Digital System (FDsys) automates the collection and dissemination of electronic information from all three branches of the United States federal government. Information is submitted directly into FDsys, permanently available in electronic format, authenticated and versioned, and publicly accessible for searching and downloading. FDsys relies on three key system components to accomplish this: 1) A content management system that securely manages digital content to safeguard content integrity and authenticity, 2) A preservation repository that follows archival system standards to ensure long-term preservation and access to digital content, and 3) An advanced search engine combines extensive metadata with modern search technology, allowing the public to find federal government publications.FDsys is a metadata driven system. It has been developed to utilize multiple metadata creation techniques, including parsing from unstructured or semi-structured text, transformations from structured formats, transformations to apply constants, and manual metadata entry. Using these techniques, GPO is able to create and store metadata to power the search engine on the FDsys.gov web site. This metadata is used to deliver advanced search, field operator search, search result filters (aka faceted navigation), and hierarchical browsing of documents. It is also used to provide downloads of descriptive metadata files in MODS XML. This emphasis on source metadata makes FDsys a dynamic, rich, flexible, powerful, and transparent system for document search and access. This paper will discuss different methods used to create metadata, how FDsys descriptive metadata is stored, and how this metadata is utilized by the FDsys search engine.

A concept-driven biomedical knowledge extraction and visualization framework for conceptualization of text corpora

A number of techniques such as information extraction, document classification, document clustering and information visualization have been developed to ease extraction and understanding of information embedded within text documents. However, knowledge that is embedded in natural language texts is difficult to extract using simple pattern matching techniques and most of these methods do not help users directly understand key concepts and their semantic relationships in document corpora, which are critical for capturing their conceptual structures. The problem arises due to the fact that most of the information is embedded within unstructured or semi-structured texts that computers can not interpret very easily. In this paper, we have presented a novel Biomedical Knowledge Extraction and Visualization framework, BioKEVis to identify key information components from biomedical text documents. The information components are centered on key concepts. BioKEVis applies linguistic analysis and Latent Semantic Analysis (LSA) to identify key concepts. The information component extraction principle is based on natural language processing techniques and semantic-based analysis. The system is also integrated with a biomedical named entity recognizer, ABNER, to tag genes, proteins and other entity names in the text. We have also presented a method for collating information extracted from multiple sources to generate semantic network. The network provides distinct user perspectives and allows navigation over documents with similar information components and is also used to provide a comprehensive view of the collection. The system stores the extracted information components in a structured repository which is integrated with a query-processing module to handle biomedical queries over text documents. We have also proposed a document ranking mechanism to present retrieved documents in order of their relevance to the user query.

A New Design Rationale Representation Model for Rationale Mining

The management of design rationale (DR) in engineering design is an important task since DR is often regarded as crucial information in design decision support and design analysis. The existing DR systems largely rely on human efforts in capturing DRs along design activities according to some predefined DR models. However, these systems require heavy human involvement and they do not have the capacity to extract DRs from design archival documents, which contain rich DR information but are usually unstructured or semistructured texts, e.g., design documents, service reports, and test reports. In view of such challenges, it has motivated us to propose a new DR model to intelligently discover DRs from design archival documents. In this paper, we propose an issue, solution and artifact layer (ISAL) model for DR representation and approaches for rationale information discovery from design archival documents. We also introduce a DR repository construction platform based on the ISAL model by integrating rationale information from both design archival documents and design processes. Using patent documents as our research data, we conduct a conceptual comparison and experimental study of DR discovery especially for artifact information extraction. Results demonstrate the merits of our proposal. Lastly, we discuss potential applications by taking advantage of our ISAL model.

A context-free markup language for semi-structured text

An ad hoc data format is any nonstandard, semi-structured data format for which robust data processing tools are not easily available. In this paper, we present ANNE, a new kind of markup language designed to help users generate documentation and data processing tools for ad hoc text data. More specifically, given a new ad hoc data source, an ANNE programmer edits the document to add a number of simple annotations, which serve to specify its syntactic structure. Annotations include elements that specify constants, optional data, alternatives, enumerations, sequences, tabular data, and recursive patterns. The ANNE system uses a combination of user annotations and the raw data itself to extract a context-free grammar from the document. This context-free grammar can then be used to parse the data and transform it into an XML parse tree, which may be viewed through a browser for analysis or debugging purposes. In addition, the ANNE system generates a PADS/ML description, which may be saved as lasting documentation of the data format or compiled into a host of useful data processing tools. In addition to designing and implementing ANNE, we have devised a semantic theory for the core elements of the language. This semantic theory describes the editing process, which translates a raw, unannotated text document into an annotated document, and the grammar extraction process, which generates a context-free grammar from an annotated document. We also present an alternative characterization of system behavior by drawing upon ideas from the field of relevance logic. This secondary characterization, which we call relevance analysis , specifies a direct relationship between unannotated documents and the context-free grammars that our system can generate from them. Relevance analysis allows us to prove important theorems concerning the expressiveness and utility of our system.

Populating Knowledge Based Decision Support Systems

Knowledge-based decision support systems (KBDSS) hold up business and organizational decision-making activities on the basis of the knowledge available concerning the domain under question. One of the main problems with knowledge bases is that their construction is a time-consuming task. A number of methodologies have been proposed in the context of the Semantic Web to assist in the development of ontology-based knowledge bases. In this paper, we present a technique for populating knowledge bases from semi-structured text which take advantage of the semantic underpinnings provided by ontologies. This technique has been tested and evaluated in the financial domain

A parallel grid-based implementation for real-time processing of event log data of collaborative applications

Collaborative applications usually register user interaction in the form of semi-structured plain text event log data. Extracting and structuring of data is a prerequisite for later key processes such as the analysis of interactions, assessment of group activity, or the provision of awareness and feedback. Yet, in real situations of online collaborative activity, the processing of log data is usually done offline since structuring event log data is, in general, a computationally costly process and the amount of log data tends to be very large. Techniques to speed and scale up the structuring and processing of log data with minimal impact on the performance of the collaborative application are thus desirable to be able to process log data in real time. In this paper, we present a parallel grid-based implementation for processing in real time the event log data generated in collaborative applications. Our results show the feasibility of using grid middleware to speed and scale up the process of structuring and processing semi-structured event log data. The Grid prototype follows the Master?Worker (MW) paradigm. It is implemented using the Globus Toolkit (GT) and is tested on the Planetlab platform.

A knowledge-anchored integrative image search and retrieval system.

Clinical data that may be used in a secondary capacity to support research activities are regularly stored in three significantly different formats: (1) structured, codified data elements; (2) semi-structured or unstructured narrative text; and (3) multi-modal images. In this manuscript, we will describe the design of a computational system that is intended to support the ontology-anchored query and integration of such data types from multiple source systems. Additional features of the described system include (1) the use of Grid services-based electronic data interchange models to enable the use of our system in multi-site settings and (2) the use of a software framework intended to address both potential security and patient confidentiality concerns that arise when transmitting or otherwise manipulating potentially privileged personal health information. We will frame our discussion within the specific experimental context of the concept-oriented query and integration of correlated structured data, narrative text, and images for cancer research.

Using structural contexts to compress semistructured text collections

We describe a compression model for semistructured documents, called Structural Contexts Model ( SCM), which takes advantage of the context information usually implicit in the structure of the text. The idea is to use a separate model to compress the text that lies inside each different structure type (e.g., different XML tag). The intuition behind SCM is that the distribution of all the texts that belong to a given structure type should be similar, and different from that of other structure types. We mainly focus on semistatic models, and test our idea using a word-based Huffman method. This is the standard for compressing large natural language text databases, because random access, partial decompression, and direct search of the compressed collection is possible. This variant, dubbed SCMHuff, retains those features and improves Huffman’s compression ratios. We consider the possibility that storing separate models may not pay off if the distribution of different structure types is not different enough, and present a heuristic to merge models with the aim of minimizing the total size of the compressed database. This gives an additional improvement over the plain technique. The comparison against existing prototypes shows that, among the methods that permit random access to the collection, SCMHuff achieves the best compression ratios, 2–4% better than the closest alternative. From a purely compression-aimed perspective, we combine SCM with PPM modeling. A separate PPM model is used to compress the text that lies inside each different structure type. The result, SCMPPM, does not permit random access nor direct search in the compressed text, but it gives 2–5% better compression ratios than other techniques for texts longer than 5 MB.

How can information extraction ease formalizing treatment processes in clinical practice guidelines?: A method and its evaluation

Formalizing clinical practice guidelines (CPGs) for a subsequent computer-supported processing is a challenging, but burdensome and time-consuming task. Existing methods and tools to support this task demand detailed medical knowledge, knowledge about the formal representations, and a manual modeling. Furthermore, formalized guideline documents mostly fall far short in terms of readability and understandability for the human domain modeler. We propose a new multi-step approach using information extraction methods to support the human modeler by both automating parts of the modeling process and making the modeling process traceable and comprehensible. This paper addresses the first steps to obtain a representation containing processes which is independent of the final guideline representation language. We have developed and evaluated several heuristics without the need to apply natural language understanding and implemented them in a framework to apply them to several guidelines from the medical subject of otolaryngology. Findings in the evaluation indicate that using semi-automatic, step-wise information extraction methods are a valuable instrument to formalize CPGs. Our evaluation shows that a heuristic-based approach can achieve good results, especially for guidelines with a major portion of semi-structured text. It can be applied to guidelines irrespective to the final guideline representation format.

Biological relation extraction and query answering from MEDLINE abstracts using ontology-based text mining

The rapid growth of the biological text data repository makes it difficult for human beings to access required information in a convenient and effective manner. The problem arises due to the fact that most of the information is embedded within unstructured or semi-structured text that computers cannot interpret very easily. In this paper we have presented an ontology-based Biological Information Extraction and Query Answering (BIEQA) System, which initiates text mining with a set of concepts stored in a biological ontology, and thereafter mines possible biological relations among those concepts using NLP techniques and co-occurrence-based analysis. The system extracts all frequently occurring biological relations among a pair of biological concepts through text mining. A mined relation is associated to a fuzzy membership value, which is proportional to its frequency of occurrence in the corpus and is termed a fuzzy biological relation. The fuzzy biological relations extracted from a text corpus along with other relevant information components like biological entities occurring within a relation, are stored in a database. The database is integrated with a query-processing module. The query-processing module has an interface, which guides users to formulate biological queries at different levels of specificity.

Hybrid specification, storage, retrieval and runtime application of clinical guidelines

Clinical guidelines are a major tool in improving the quality of medical care. However, most guidelines are in free text, are not machine-comprehensible and are not easily accessible to clinicians at the point of care. We have designed and implemented a web-based, modular, distributed architecture, the Digital Electronic Guideline Library (DeGeL), which facilitates gradual conversion of clinical guidelines from text to a formal representation in the chosen target guideline ontology. The architecture supports guideline classification, semantic markup, context-sensitive search, browsing, run-time application and retrospective quality assessment. The DeGeL hybrid meta-ontology includes elements common to all guideline ontologies, such as semantic classification and domain knowledge; it also includes four content-representation formats: free text, semi-structured text, semi-formal representation and a formal representation. These formats support increasingly sophisticated computational tasks. Guidelines can thus be in a hybrid representation in which guidelines, and even parts of the same guideline, might exist at different formalisation levels. We have also developed and rigorously evaluated a methodology and an associated web-based tool, Uruz, for gradually structuring and semi-formalising free-text clinical guidelines. Finally, we have designed, implemented and evaluated a new approach, the hybrid runtime application model, for supporting runtime application of clinical guidelines that are not necessarily in a machine-comprehensible format; in particular, when the guideline is in a semi-formal representation and the patient's data are either in an electronic medical record or in a paper format. The tool implementing this new approach, the Spock module, is customised at this point to the Asbru guideline specification language and exploits the hybrid structure of guidelines in DeGeL. The Spock module also exploits our temporal-abstraction mediator to the patient record, IDAN, and our interactive intelligent-visualisation tool, KNAVE-II.

GLOBAL RULE INDUCTION FOR INFORMATION EXTRACTION

The ability to extract desired pieces of information from natural language texts is an important task with a growing number of potential applications. This paper presents a novel pattern rule induction learning system, GRID, which emphasizes the use of global feature distribution in all of the training instances in order to make better decision on rule induction. GRID uses chunks as contextual units instead of tokens, and incorporates features at lexical, syntactical and semantic levels simultaneously. The features chosen in GRID are general and they were applied successfully to both semi-structured text and free text. Our experimental results on some publicly available webpage corpora and MUC-4 test set indicate that our approach is effective.

A framework for a distributed, hybrid, multiple-ontology clinical-guideline library, and automated guideline-support tools

Clinical guidelines are a major tool in improving the quality of medical care. However, most guidelines are in free text, not in a formal, executable format, and are not easily accessible to clinicians at the point of care. We introduce a Web-based, modular, distributed architecture, the Digital Electronic Guideline Library (DeGeL), which facilitates gradual conversion of clinical guidelines from text to a formal representation in chosen target guideline ontology. The architecture supports guideline classification, semantic markup, context-sensitive search, browsing, run-time application, and retrospective quality assessment. The DeGeL hybrid meta-ontology includes elements common to all guideline ontologies, such as semantic classification and domain knowledge; it also includes four content-representation formats: free text, semi-structured text, semi-formal representation, and a formal representation. These formats support increasingly sophisticated computational tasks. The DeGeL tools for support of guideline-based care operate, at some level, on all guideline ontologies. We have demonstrated the feasibility of the architecture and the tools for several guideline ontologies, including Asbru and GEM.

Knowledge modeling and acquisition of traditional Chinese herbal drugs and formulae from text

Traditional Chinese medicine has developed over more than 4000 years. A tremendous amount of medical knowledge has been accumulated, among which herbal drugs and formulae are an important portion. This paper presents an ontology for traditional Chinese drugs and formulae, and an ontology-based system for extracting knowledge of drugs and formulae from semi-structured text. The system consists of two components: an executable knowledge extraction language (or EKEL) for specifying knowledge-extracting agents, and a support machine for executing EKEL programs. Experiments show that the system is adequate of extracting knowledge of herbal drugs and formulae from semi-structured text.