Concept Relation Extraction from Construction Documents Using Natural Language Processing

The objective of this research is to present an innovative technique for managing the knowledge contained in construction contract documents to facilitate quick access and efficient use of such knowledge for project management and contract administration tasks. Knowledge Management has become the focus of a lot of scientific research during the second half of the 20th century as researchers discovered the importance of the knowledge resource to business organizations. Despite early expectations of improved document management techniques, document management systems used in the construction industry have failed to deliver the anticipated performance. Recent research attempts to utilize analysis of the contents of documents to improve document categorization and retrieval functions. It is hypothesized that natural language processing can be effectively used to perform document text analysis. The proposed system, technique for concept relation identification using shallow parsing (CRISP), utilizes a shallow parser to extract semantic knowledge from construction contract documents which can be used to improve electronic document management functions such as document categorization and retrieval. When compared with human evaluators, CRISP achieved almost 80% of the average kappa score attained by the evaluators, and approximately 90% of their F-measure score.     

Automated Classification of Construction Project Documents

The number of documents generated in a construction project and stored in interorganizational information systems is significant. Since a large percentage of these project documents are generated in text format, methods for organizing and improving access to the information contained in these types of documents become essential to construction information management. Information classification schemes can be used for this purpose. They provide a common framework to enact document organization and information exchange among project members. Current systems for document management rely on manual classification methods controlled by human experts. Due to the widespread use of information technologies for construction, the increasing availability of electronic documents, and the development of systems based on project object models, manual classification becomes unfeasible. This paper presents a unique way to improve information organization and access in interorganizational systems based on automated classification of construction project documents according to their related project components. Machine learning methods were used for this purpose. A prototype of a document classification system was developed to provide easy deployment and scalability to the classification process.     

Ontology-Based Approach to Context Representation and Reasoning for Managing Context-Sensitive Construction Information

The construction industry is an information-intensive industry and heavily relies on documents, including physical and virtual documentation and models, to exchange context-sensitive information among different project participants. Many research efforts have been made to help manage construction information; however, few of them considered the context-sensitive nature of the information. In this paper, the writers propose a new approach to facilitate the management of context-sensitive construction information that is stored in different textual documents. The approach addresses the context-sensitive nature of construction information by representing contexts in ontologies and by using contexts as indices of the information. The approach also presents a reasoning mechanism that leverages the semantically rich features of ontologies to reason about contexts to evaluate their applicabilities. Two case studies were conducted, and the results showed the proposed approach can effectively retrieve, classify, and manage construction information. Finally, the writers discuss the limitations of the proposed approach and future research directions.     

Options for the management of mucosal candidiasis in patients with AIDS and HIV infection

OBJECTIVE: To design a document model that provides reliable and efficient access to clinical information in patient reports for a broad range of clinical applications, and to implement an automated method using natural language processing that maps textual reports to a form consistent with the model. METHODS: A document model that encodes structured clinical information in patient reports while retaining the original contents was designed using the extensible markup language (XML), and a document type definition (DTD) was created. An existing natural language processor (NLP) was modified to generate output consistent with the model. Two hundred reports were processed using the modified NLP system, and the XML output that was generated was validated using an XML validating parser. RESULTS: The modified NLP system successfully processed all 200 reports. The output of one report was invalid, and 199 reports were valid XML forms consistent with the DTD. CONCLUSIONS: Natural language processing can be used to automatically create an enriched document that contains a structured component whose elements are linked to portions of the original textual report. This integrated document model provides a representation where documents containing specific information can be accurately and efficiently retrieved by querying the structured components. If manual review of the documents is desired, the salient information in the original reports can also be identified and highlighted. Using an XML model of tagging provides an additional benefit in that software tools that manipulate XML documents are readily available.     

Multimodal Image Retrieval from Construction Databases and Model-Based Systems

In the modern and dynamic construction environment it is important to access information in a fast and efficient manner in order to improve the decision making processes for construction managers. This capability is, in most cases, straightforward with today’s technologies for data types with an inherent structure that resides primarily on established database structures like estimating and scheduling software. However, previous research has demonstrated that a significant percentage of construction data is stored in semi-structured or unstructured data formats (text, images, etc.) and that manually locating and identifying such data is a very hard and time-consuming task. This paper focuses on construction site image data and presents a novel image retrieval model that interfaces with established construction data management structures. This model is designed to retrieve images from related objects in project models or construction databases using location, date, and material information (extracted from the image content with pattern recognition techniques).     

非正式出版电子文献的管理与利用

介绍了非正式出版电子文献的几个特点,指出在高校此类文献具有广活的信息源,同时艰高校非正式电子文献的管理及需要注意的几个文献作了一些有益的探索。     

对工程项目管理系统的认识

工程项目管理系统是企业信息系统中关键的子系统。用于指导和协调其它子系统之间业务传递和数据共享。针对工程项目管理存在的信息沟通困难、数据易变化、书面文档多的难点，在建立工程项目管理系统时。可通过计算机网络系统、信息沟通系统、电子文档管理系统、项目数据管理系统等来实现对工程项目的管理。     

Implementing Observational Research Methods to Study Team Performance in Construction Management

The evolution of research in the area of construction engineering and management has moved toward the use of quantitative metrics and research methods for identifying and evaluating the impact of events or procedures on the construction process. While quantitative research methods can be very important for answering certain research questions, there are important reasons for adopting qualitative or mixed methodology studies to gain a better understanding of complex phenomena. This paper explores the use of observational studies and their potential use within the field of construction research. Observational studies can provide answers to “what” phenomena occurred, particularly when people are involved in a process, along with gaining insights into “why” the phenomena occurred. This paper discusses two types of observational studies, structured and unstructured, and provides a procedure for their implementation within construction research. To clearly demonstrate the methodology, a case study focused on the investigation of two different versions of an educational simulation application, the virtual construction simulator (VCS), is used to illustrate the benefits and challenges of implementing mixed methodology observational studies. The case study involved the video recording and analysis of interactions between student team members when using the VCS application for a construction sequencing task. The video recordings were analyzed, and important insights were identified, both qualitative and quantitative. Through content analysis, it was determined that the improvements made in a new version of the VCS application were beneficial, and the detailed observational studies identified insights into why the revisions in the application yielded improved results. This case study details the steps and considerations involved in planning an observational study, as well as the benefits and challenges that researchers may encounter when using observational research methodologies.     

Prototype Web-Based Construction Project Management System

This paper presents a conceptual model of a metadata-based information system for data exchange among Web-based documents for construction project management. The system retrieves useful data from the original documents, reorganizes the information according to specific tasks or users, and displays the information in an integrated web page. The study identifies the comprehensive functional requirements from existing Web-based collaboration systems, and finds out new user requirements by way of a Web-based survey in Singapore. Based on the requirement studies, a prototype model is developed using unified modeling language. Implementation of the conceptual model uses extensible markup language technology. Discussions on major concerns about information security, data accessibility, and service quality are included in this paper.     

Determination of Key Performance Indicators with Enterprise Resource Planning Systems in Engineering Construction Firms

The study focuses on developing a unified approach to define information specificities for key performance indicators (KPIs). Borrowing from the time-system theory, the paper defines different types of KPI and identifies that a KPI has two dimensions—knowledge specificity and time specificity. Different approaches are presented to analyze knowledge and time sensitivities. This paper addresses a key question related to enterprise resource planning (ERP) systems applications in the engineering construction industry: what are the areas of business processes within the engineering construction industry where ERP cannot be used to collect KPIs related to business processes? The writers review empirical and specialized processes within the construction industry to identify business processes not covered by existing ERP systems. A survey focused on qualitative aspects of ERP systems implementation in engineering construction firms was conducted among ERP-enablers in the construction industry and provided a basis for the presented case study. Data collected are from major engineering and construction firms in the United States and therefore the results are relevant for researchers and industry practitioners concerned with application of enterprise management systems in the respective firms.     

Exploring the Effectiveness of Chinese-to-English Machine Translation for CLIR Applications in Earthquake Engineering

Machine translation is able to support cross-language information retrieval (CLIR) applications given the availability of high-quality translation resources. This study explores the effectiveness of machine translation for the domain of earthquake engineering within the bounds of Chinese-to-English CLIR applications. The writers first defined and then applied a set of procedures to generate Chinese-to-English translation resources for the selected domain. The generated resources are unique and different from general dictionaries or corpora because they address the Chinese segmentation process and are especially oriented for information retrieval (IR) applications. To test the quality of the resources, the writers converted a test collection of documents from Chinese into English through machine translation and conducted trial retrieval runs on the translated documents using different retrieval models. For comparison purposes, the same retrieval runs were also tested on the expert-written English translations. The results suggest that IR-based machine translation was able to yield results comparable to that of human translation and the generated resources had the potential to enable greater sharing of earthquake engineering information across languages while reducing manual translation efforts.     

Document Structure and Its Effect on Engineers’ Reading Strategies

Seven hundred and forty four professional engineers in training courses on engineering documentation were given two versions of a text containing identical information. One version was structured as a linear argument leading up to the main item of information at the end; the other was structured so that a document summary was placed at the beginning, and the remaining text formatted so that the detail lay under a series of section summaries. They were asked to choose the version that most aided their information retrieval and to analyze their methods of extracting detailed information from both texts. They unanimously preferred the second version. All participants first read the summary (Abstract in this case) then read the section summaries in sequence. They then regressed to read the detail associated with each section summary. It is proposed that when reading a technical document, we look for overview information at successive levels of detail. Using this principle, documents can be designed to incorporate a navigational route of overview information; this will aid both the expert and nonexpert reader to obtain the individually required level of detail.     

Integrating Document Management with Project and Company Data

Electronic document management (EDM) systems have revolutionized the construction document storage and retrieval process. An electronically managed document consists of a computer representation of the main document body, usually in the form of a bitmap, and a reference or indexing structure used to retrieve the document. In construction, the reference data includes information that relates the document to certain aspects of the constructed facility and the construction company. It is argued that this relationship needs to be represented explicitly and in an integrated manner as opposed to the approach used by traditional EDM systems. This paper presents an integrated approach based on the concept of specialized construction data models. A detailed account of how this approach was followed to integrate a quality assurance document management system within a steel fabrication company is also presented.     

论附盘文献管理的推陈出新

附盘文献是近年来出现的一种介于图书和电子出版物之间的新型文献，是图书馆文献资源中新的组成部分。有关部门应制定统一的标准以全面标升图书馆的管理和服务水平。     

Natural language generation in health care

Good communication is vital in health care, both among health care professionals, and between health care professionals and their patients. And well-written documents, describing and/or explaining the information in structured databases may be easier to comprehend, more edifying, and even more convincing than the structured data, even when presented in tabular or graphic form. Documents may be automatically generated from structured data, using techniques from the field of natural language generation. These techniques are concerned with how the content, organization and language used in a document can be dynamically selected, depending on the audience and context. They have been used to generate health education materials, explanations and critiques in decision support systems, and medical reports and progress notes.     

Dynamic Three-Dimensional Visualization of Fluid Construction Materials

The presented work extends the state-of-the-art of visualizing discrete-event construction simulations in three dimensions (3D). Efficient methods are presented along with a tool, ParticleWorks, that can be used to animate simulated construction processes that involve unstructured, fluid construction materials as resources or byproducts. Common construction processes that involve such fluid materials include placing concrete, dumping dirt, shotcreting, sandblasting, dewatering, water distribution, and inserting slurry. The writers capitalize on a classical computer graphics concept called particle systems to design simple, simulation model-authorable, parametric-text methods that can describe arbitrary volumes of dynamic fluid construction materials in animated 3D virtual construction worlds. These methods can be used to instrument discrete-event simulation models (or other external authoring interfaces) to automatically generate dynamic visualizations of any modeled construction operations that commonly handle and process fluid construction materials.     

Cost Information Model for Managing Multiple Projects

Construction companies must deal with several projects at once, but a system to manage multiple projects is not fully developed yet. The first step towards developing such system is to design an information model that is suitable for managing multiple projects. This paper presents the cost-based project modeling (CBPM) method in contrast to the traditional activity-based project modeling methods. The CBPM uses cost as a core of the model along with other project information organized around it. The CBPM serves as a platform for integrating project information from multiple projects. Various types of construction costs are hierarchically modeled to generate corporate-wide information such as project performances, cash flows, and other predictive indicators. Based on the information model, an object-oriented database was developed to contain cost data across several projects. In the model, a module that connects to external systems is built into the model to enhance interactivity with the legacy systems and the industry standards. A prototype system was developed and tested with actual project data to validate the information processing capabilities of the model. The findings from the test indicate construction cost can be an excellent medium that can organize various types of information of multiple projects.     

Comparative Study of Idea Generation between Traditional Value Management Workshops and GDSS-Supported Workshops

Value management (VM) has been widely used to meet challenges arising from the construction industry. However, it has also encountered some problems such as passive participation in VM workshops and a lack of time and information to complete all tasks in the workshops. A group decision support system (GDSS), entitled interactive value management system (IVMS), has been developed by the writers to overcome these problems. This paper starts with an introduction to GDSS and a critical review of technologies used in the process of idea generation in VM workshops. This is followed by findings of a laboratory experiment designed to compare the productivity of traditional brainstorming and brainstorming with IVMS support in VM workshops. The results of the experiment showed that IVMS has a positive influence on idea generation in VM workshops. Finally, the implications of the study and directions for future research are discussed.     

Action Research as a Proactive Research Method for Construction Engineering and Management

Academic research in applied disciplines such as construction engineering and management (CEM) has the dual mission of simultaneously contributing to the solution of practical problems and creating theoretical and conceptual knowledge. To do so, appropriate research approaches are needed. However, extant literature in the field has paid little attention to this issue and research methods used have been almost entirely either quantitative surveys or case studies. In this paper, action research (AR) is proposed as an answer to this knowledge gap. AR aims at building and testing theory within the context of solving an immediate practical problem in a real setting. The paper describes the underlying philosophy and application procedure of AR and highlights its strengths and weaknesses. Then, the applicability of the method to CEM is illustrated through a case study of improving access to information to support planning and decision making in a construction owner organization through designing and implementing a data warehouse. The findings indicate that AR is a reliable, structured, and rigorous research approach that is very useful for conducting applied research in construction and enabling academia to influence and improve construction industry practices. It can also effectively help to improve collaboration between academic researchers and industry practitioners in research and development projects.