Towards concept identification using a knowledge-intensive approach

This paper presents a method for identifying concepts in microposts and classifying them into a predefined set of categories. The method relies on the DBpedia knowledge base to identify the types of the concepts detected in the messages. For those concepts that are not classified in the ontology we infer their types via the ontology properties which characterise the type.

Género y transporte: análisis de la movilidad del cuidado como punto de partida para construir una base de conocimiento más amplia de los patrones de movilidad. El caso de Madrid

Las limitaciones en la capacidad de movilidad pueden ser consideradas en la actualidad como una forma de discriminación tremenda y a la vez invisible dentro de la sociedad. Para poder evitar esta discriminación es necesario que las políticas de transporte, que hasta ahora han basado sus actuaciones particularmente sobre las necesidades de acceso al empleo, reconozcan las exigencias de las personas dependientes y de aquellas que realizan las tareas no remuneradas del cuidado de otros y de atención a la familia. Las personas que trabajan en las tareas domésticas, en la mayoría de los casos mujeres, tienen muchas dificultades para sincronizar sus obligaciones con los tiempos y las distancias. Estas personas desempeñan un trabajo diario, que tiene lugar tanto fuera como dentro del hogar y tienen necesidades específicas de movilidad. El problema principal es que este tipo de trabajo no suele ser tomado en consideración, ya que no entra en la esfera del trabajo remunerado. Pero es una labor que está estrictamente ligada a la actividad de la sociedad y es un elemento indispensable para el funcionamiento de la vida urbana. Es un trabajo real, que tiene lugar en el espacio urbano, que exige un considerable esfuerzo físico y emocional, y que ayuda a garantizar la calidad de la vida cotidiana. Es un aspecto indispensable a tener en cuenta en el ejercicio de las políticas públicas y sociales. Sobre la base de estas consideraciones se introduce el concepto “Movilidad del cuidado” (Sánchez de Madariaga, 2009a y 2009b), mediante el cual se reconoce la necesidad de evaluar y hacer visible los desplazamientos diarios asociados con el trabajo del cuidado. Por trabajo del cuidado se entiende el trabajo no remunerado, realizado por los adultos para los niños u otras personas dependientes, incluido el trabajo relacionado con el mantenimiento del hogar. El análisis de este tipo de viajes exige ciertos cambios significativos en las formas de recoger datos estadísticos. No se trata solo de sumar los desplazamientos que actualmente aparecen en las estadísticas como viajes de compras, acompañamiento, gestiones, cuidado de otros, etc. El problema es que los datos sobre movilidad se recogen con una serie de sesgos que infravaloran los viajes de cuidado: las estadísticas no cuentan los viajes cortos a pie y tampoco reflejan bien los viajes encadenados, ambos típicamente femeninos; no se deslindan con precisión los viajes de cuidado de otro tipo de viajes, de manera que muchos desplazamientos relacionados con la esfera reproductiva aparecen como viajes personales o de ocio y en muchos casos se encasillan en la categoría otros. Mediante esta investigación se pretende estimar el peso que la movilidad del cuidado tiene en el total de la movilidad y describirla de manera precisa en un contexto geográfico determinado, en el caso específico Madrid. Los estudios sobre el tema realizados hasta el momento reconocen la necesidad de llevar a cabo encuestas de movilidad que tengan en cuenta las variables socio económicas que caracterizan a la población y también se demanda la segregación de los datos recogidos por sexo, así como el uso del género como una categoría analítica. Igualmente es indispensable atribuir la misma importancia que tienen los viajes relacionados con la esfera productiva a los que están relacionados con la esfera reproductiva. No obstante, es solo mediante la introducción del concepto de “movilidad del cuidado” que se propone una nueva categorización de los motivos de desplazamiento dentro de las “clásicas” encuestas de movilidad y, por primera vez, mediante esta investigación se aplica este concepto a un ejemplo práctico a partir del cual queda en evidencia la necesidad de un cambio de enfoque en las políticas de transporte. Así, a través el uso de encuestas cuantitativas y cualitativas realizadas ad hoc sobre la base de la metodología propuesta, se capturan los patrones de viajes significativos para poder describir en maneara exhaustiva la movilidad de las personas que tienen responsabilidades de cuidado. El objetivo es crear una base de conocimiento más amplia sobre los patrones de movilidad, comportamientos y necesidades, además de mejorar los conceptos operacionales y establecer políticas de transporte más equitativas, que respondan de mejor manera a las necesidades de género, beneficiando así a toda la sociedad. ABSTRACT Nowadays, limitations in urban mobility can be considered as some type of extreme discrimination, which remains invisible to the society. In order to avoid this kind of discrimination, new transport policies are required, especially considering that so far they have been based and organized particularly in relation to the needs derived from the access to employment. These policies must take into account the demands of people depending on the support of others as well as of unpaid caregivers in charge of looking after other individuals and taking care of the family. Most of the people devoted to domestic work, which in the vast majority of cases is carried out by women, find it difficult to coordinate their obligations with time and distances. These people carry out a daily job that takes place both inside their homes as well as outside, and they have specific mobility needs. The main issue is that this type of work is usually not taken into consideration, since it is not included under the scope of paid employment. However, this work is strictly related to the activities of society and is therefore a crucial element in the functioning of urban life. It is an actual job that takes place in an urban space, requires a considerable amount of physical and emotional effort and guarantees quality of life on a daily basis. This is an important aspect that should be taken into account when drafting public and social policies. The concept of “Mobility of care” (Sánchez de Madariaga, 2009a and 2009b) is introduced under these considerations. This concept acknowledges the need to evaluate and identify daily movements from one place to another that are related to caregiving. Caregiving is understood, in this case, as unpaid work that is carried out by adults for children and other people that depend on the support of others, and it also includes duties related to home maintenance. The analysis of these types of movements requires some significant changes in the way in which statistic data is gathered. The idea is to not only add up the movements that appear in statistics such as shopping trips, accompanying someone, dealings, caregiving, etc. The problem with data on mobility is that it is gathered with bias that undervalues mobility related to caregiving: statistics do not take into consideration short trips that are made walking nor do they properly reflect connected trips, both of which are typically feminine; moreover, there is an imprecise differentiation of trips related to caregiving and other kind of trips, and because of that, many of the trips related to the reproductive sphere are considered personal or recreational trips, and are many times labelled as others. This investigation aims to evaluate the importance that mobility of care has in mobility in general, describing it in a precise manner within a specific geographical context that in this case is Madrid. To this date, most of the studies on this subject have acknowledged the need to carry out mobility surveys that include socio economic variables that characterize the population and they have also requested that collected data is segregated by sex and that gender is used as an analytical category. Likewise, it is fundamental to give the same importance to mobility related to the sphere of reproduction as to that related to the sphere of productiveness. However, it is only through the implementation of the concept of “mobility of care” that a new categorization of mobility, within classic mobility surveys, is proposed. Also, for the first time and by this investigation, this concept is applied to a practical case, shining a light on the need to change the focus of transport policies. Through the use of ad hoc quantitative and qualitative surveys based on the proposed methodology, the patterns of relevant movements are identified in order to thoroughly describe the mobility of people responsible of caregiving. The aim is to create a broader knowledge base on patterns of mobility, behaviour and necessities, in addition to improving functional concepts and transport policies to make them more equitable and responsive to gender needs, thus benefitting society as a whole.

An authoring tool for decision support systems in context questions of ecological knowledge

Decision support systems (DSS) support business or organizational decision-making activities, which require the access to information that is internally stored in databases or data warehouses, and externally in the Web accessed by Information Retrieval (IR) or Question Answering (QA) systems. Graphical interfaces to query these sources of information ease to constrain dynamically query formulation based on user selections, but they present a lack of flexibility in query formulation, since the expressivity power is reduced to the user interface design. Natural language interfaces (NLI) are expected as the optimal solution. However, especially for non-expert users, a real natural communication is the most difficult to realize effectively. In this paper, we propose an NLI that improves the interaction between the user and the DSS by means of referencing previous questions or their answers (i.e. anaphora such as the pronoun reference in “What traits are affected by them?”), or by eliding parts of the question (i.e. ellipsis such as “And to glume colour?” after the question “Tell me the QTLs related to awn colour in wheat”). Moreover, in order to overcome one of the main problems of NLIs about the difficulty to adapt an NLI to a new domain, our proposal is based on ontologies that are obtained semi-automatically from a framework that allows the integration of internal and external, structured and unstructured information. Therefore, our proposal can interface with databases, data warehouses, QA and IR systems. Because of the high NL ambiguity of the resolution process, our proposal is presented as an authoring tool that helps the user to query efficiently in natural language. Finally, our proposal is tested on a DSS case scenario about Biotechnology and Agriculture, whose knowledge base is the CEREALAB database as internal structured data, and the Web (e.g. PubMed) as external unstructured information.

A Knowledge-based System for Intelligent Support in Pharmacogenomics Evidence Assessment: Ontology-driven Evidence Representation, Retrieval, Classification and Interpretation

Thesis (Ph.D.)--University of Washington, 2016-06

User interface design support for the development of knowledge-based systems

The present scarcity of operational knowledge-based systems (KBS) has been attributed, in part, to an inadequate consideration shown to user interface design during development. From a human factors perspective the problem has stemmed from an overall lack of user-centred design principles. Consequently the integration of human factors principles and techniques is seen as a necessary and important precursor to ensuring the implementation of KBS which are useful to, and usable by, the end-users for whom they are intended. Focussing upon KBS work taking place within commercial and industrial environments, this research set out to assess both the extent to which human factors support was presently being utilised within development, and the future path for human factors integration. The assessment consisted of interviews conducted with a number of commercial and industrial organisations involved in KBS development; and a set of three detailed case studies of individual KBS projects. Two of the studies were carried out within a collaborative Alvey project, involving the Interdisciplinary Higher Degrees Scheme (IHD) at the University of Aston in Birmingham, BIS Applied Systems Ltd (BIS), and the British Steel Corporation. This project, which had provided the initial basis and funding for the research, was concerned with the application of KBS to the design of commercial data processing (DP) systems. The third study stemmed from involvement on a KBS project being carried out by the Technology Division of the Trustees Saving Bank Group plc. The preliminary research highlighted poor human factors integration. In particular, there was a lack of early consideration of end-user requirements definition and user-centred evaluation. Instead concentration was given to the construction of the knowledge base and prototype evaluation with the expert(s). In response to this identified problem, a set of methods was developed that was aimed at encouraging developers to consider user interface requirements early on in a project. These methods were then applied in the two further projects, and their uptake within the overall development process was monitored. Experience from the two studies demonstrated that early consideration of user interface requirements was both feasible, and instructive for guiding future development work. In particular, it was shown a user interface prototype could be used as a basis for capturing requirements at the functional (task) level, and at the interface dialogue level. Extrapolating from this experience, a KBS life-cycle model is proposed which incorporates user interface design (and within that, user evaluation) as a largely parallel, rather than subsequent, activity to knowledge base construction. Further to this, there is a discussion of several key elements which can be seen as inhibiting the integration of human factors within KBS development. These elements stem from characteristics of present KBS development practice; from constraints within the commercial and industrial development environments; and from the state of existing human factors support.

Knowledge management in knowledge intensive service networks:a strategic management approach

Purpose – The main purpose of this paper is to analyze knowledge management in service networks. It analyzes the knowledge management process and identifies related challenges. The authors take a strategic management approach instead of a more technology-oriented approach, since it is believed that managerial problems still remain after technological problems are solved. Design/methodology/approach – The paper explores the literature on the topic of knowledge management as well as the resource (or knowledge) based view of the firm. It offers conceptual insights and provides possible solutions for knowledge management problems. Findings – The paper discusses several possible solutions for managing knowledge processes in knowledge-intensive service networks. Solutions for knowledge identification/generation, knowledge application, knowledge combination/transfer and supporting the evolution of tacit network knowledge include personal and technological aspects, as well as organizational and cultural elements. Practical implications – In a complex environment, knowledge management and network management become crucial for business success. It is the task of network management to establish routines, and to build and regularly refresh meta-knowledge about the competencies and abilities that exist within the network. It is suggested that each network partner should be rated according to the contribution to the network knowledge base. Based on this rating, a particular network partner is a member of a certain knowledge club, meaning that the partner has access to a particular level of network knowledge. Such an established routine provides strong incentives to add knowledge to the network's knowledge base Originality/value – This paper is a first attempt to outline the problems of knowledge management in knowledge-intensive service networks and, by so doing, to introduce strategic management reasoning to the discussion.

An Idea of a Computer Knowledge Bank on Medical Diagnostics

The paper is a description of information and software content of a computer knowledge bank on medical diagnostics. The classes of its users and the tasks which they can solve are described. The information content of the bank contains three ontologies: an ontology of observations in the field of medical diagnostics, an ontology of knowledge base (diseases) in medical diagnostics and an ontology of case records, and also it contains three classes of information resources for every division of medicine – observation bases, knowledge bases, and data bases (with data about patients), that correspond to these ontologies. Software content consists of editors for information of different kinds (ontologies, bases of observations, knowledge and data), and also of a program which performs medical diagnostics.

Representing human expertise by the OWL web ontology language to support knowledge engineering in decision support systems

Clinical decision support systems (CDSSs) often base their knowledge and advice on human expertise. Knowledge representation needs to be in a format that can be easily understood by human users as well as supporting ongoing knowledge engineering, including evolution and consistency of knowledge. This paper reports on the development of an ontology specification for managing knowledge engineering in a CDSS for assessing and managing risks associated with mental-health problems. The Galatean Risk and Safety Tool, GRiST, represents mental-health expertise in the form of a psychological model of classification. The hierarchical structure was directly represented in the machine using an XML document. Functionality of the model and knowledge management were controlled using attributes in the XML nodes, with an accompanying paper manual for specifying how end-user tools should behave when interfacing with the XML. This paper explains the advantages of using the web-ontology language, OWL, as the specification, details some of the issues and problems encountered in translating the psychological model to OWL, and shows how OWL benefits knowledge engineering. The conclusions are that OWL can have an important role in managing complex knowledge domains for systems based on human expertise without impeding the end-users' understanding of the knowledge base. The generic classification model underpinning GRiST makes it applicable to many decision domains and the accompanying OWL specification facilitates its implementation.

Teacher talk: A community of colleagues that values practical teacher knowledge through sharing experiences

The purpose of this study was to describe the experiences of five educators participating in a teacher-initiated learning community that valued practical teacher knowledge. Connelly and Clandinin (2000) argued that practical teacher knowledge grew out of experience through interaction in the professional knowledge landscape. Collaboration that promoted teacher learning was the foundation to effective school change (Wood, 1997). This teacher-initiated learning community consisted of members who had equal status and collaborated by participating in discourse on curriculum and instruction. The collegiality of the community fostered teacher professionalism that improved practice and benefited the school. This study focused on the following research questions: (1) What was the experience of these five educators in this learning community? (2) What did these five individuals understand about the nature of practical teacher knowledge? (3) According to the participants, what was the relationship between teacher empowerment and effective school change? ^ The participants were chosen because each voluntarily attended this teacher-initiated learning community. Each participant answered questions regarding the experience during three semi-structured tape-recorded interviews. The interviews were transcribed, and significant statements of meaning were extracted. Using a triangulation of ideas that were common to at least three of the participants ensured the trustworthiness of the analysis. These statements were combined to describe what was experienced and how the participants described their experience. The emerging themes were the characteristics of and the relationships, methods, conditions, and environment for the teachers. The teachers described how a knowledge base of practical teacher knowledge was gained as a spirit of camaraderie developed. The freedom that the teachers experienced to collaborate and learn fostered new classroom practice that affected school change as student interaction and productivity increased. ^ The qualitative analysis of this study provided a description of a learning community that valued practical teacher knowledge and fostered professional development. This description was important to educational stakeholders because it demonstrated how practical teacher knowledge was gained during the teachers' daily work. By sharing every day experiences, the teacher talk generated collaboration and accountability that the participants felt improved practice and fostered a safe, productive learning environment for students. ^

The role of market knowledge in recognizing and exploiting entrepreneurial opportunities in technology intensive firms

Entrepreneurial opportunity recognition is an increasingly prevalent phenomenon. Of particular interest is the ability of promising technology based ventures to recognize and exploit opportunities. Recent research drawing on the Austrian economic theory emphasizes the importance of knowledge, particularly market knowledge, behind opportunity recognition. While insightful, this research has tended to overlook those interrelationships that exist between different types of knowledge (technology and market knowledge) as well as between a firm’s knowledge base and its entrepreneurial orientation. Additional shortfalls of prior research include the ambiguous definitions provided for entrepreneurial opportunities, oversight of opportunity exploitation with an extensive focus on opportunity recognition only, and the lack of quantitative, empirical evidence on entrepreneurial opportunity recognition. ^ In this dissertation, these research gaps are addressed by integrating Schumpeterian opportunity development view with a Kirznerian opportunity discovery theory as well as insights from literature on entrepreneurial orientation. A sample of 85 new biotechnology ventures from the United States, Finland, and Sweden was analyzed. While leaders in all 85 companies were interviewed for the research in 2003-2004, 42 firms provided data in 2007. Data was analyzed using regression analysis. ^ The results show the value and importance of early market knowledge and technology knowledge as well as an entrepreneurial company posture for subsequent opportunity recognition. The highest numbers of new opportunities are recognized in firms where high levels of market knowledge are combined with high levels of technology knowledge (measured with a number of patents). A firm’s entrepreneurial orientation also enhances its opportunity recognition. Furthermore, the results show that new ventures with more market knowledge are able to gather more equity investments, license out more technologies, and achieve higher sales than new ventures with lower levels of market knowledge. Overall, the findings of this dissertation help further our understanding of the sources of entrepreneurial opportunities, and should encourage further research in this area. ^

The role of market knowledge in recognizing and exploiting entrepreneurial opportunities in technology intensive firms

Entrepreneurial opportunity recognition is an increasingly prevalent phenomenon. Of particular interest is the ability of promising technology based ventures to recognize and exploit opportunities. Recent research drawing on the Austrian economic theory emphasizes the importance of knowledge, particularly market knowledge, behind opportunity recognition. While insightful, this research has tended to overlook those interrelationships that exist between different types of knowledge (technology and market knowledge) as well as between a firm’s knowledge base and its entrepreneurial orientation. Additional shortfalls of prior research include the ambiguous definitions provided for entrepreneurial opportunities, oversight of opportunity exploitation with an extensive focus on opportunity recognition only, and the lack of quantitative, empirical evidence on entrepreneurial opportunity recognition. In this dissertation, these research gaps are addressed by integrating Schumpeterian opportunity development view with a Kirznerian opportunity discovery theory as well as insights from literature on entrepreneurial orientation. A sample of 85 new biotechnology ventures from the United States, Finland, and Sweden was analyzed. While leaders in all 85 companies were interviewed for the research in 2003-2004, 42 firms provided data in 2007. Data was analyzed using regression analysis. The results show the value and importance of early market knowledge and technology knowledge as well as an entrepreneurial company posture for subsequent opportunity recognition. The highest numbers of new opportunities are recognized in firms where high levels of market knowledge are combined with high levels of technology knowledge (measured with a number of patents). A firm’s entrepreneurial orientation also enhances its opportunity recognition. Furthermore, the results show that new ventures with more market knowledge are able to gather more equity investments, license out more technologies, and achieve higher sales than new ventures with lower levels of market knowledge. Overall, the findings of this dissertation help further our understanding of the sources of entrepreneurial opportunities, and should encourage further research in this area.

The Relationship between Classroom Interactions and Exclusionary Discipline as a Social Practice: A Critical Microethnography

Exclusionary school discipline results in students being removed from classrooms as a consequence of their disruptive behavior and may lead to subsequent suspension and/or expulsion. Literature documents that nondominant students, particularly Black males, are disproportionately impacted by exclusionary discipline, to the point that researchers from a variety of critical perspectives consider exclusionary school discipline an oppressive educational practice and condition. Little or no research examines specific teacher-student social interactions within classrooms that influence teachers’ decisions to use or not use exclusionary discipline. Therefore, this study set forth the central research question: In relation to classroom interactions in alternative education settings, what accounts for teachers’ use or non-use of exclusionary discipline with students? A critical social practice theory of learning served as the framework for exploring this question, and a critical microethnographic methodology informed the data collection and analysis. Criterion sampling was used to select four classrooms in the same alternative education school with two teachers who frequently and two who rarely used exclusionary discipline. Nine stages of data collection and reconstructive data analysis were conducted. Data collection involved video recorded classroom observations, digitally recorded interviews of teachers and students discussing selected video segments, and individual teacher interviews. Reconstructive data analysis procedures involved hermeneutic inferencing of possible underlying meanings, critical discourse analysis, interactive power analysis and role analysis, thematic analysis of the interactions in each classroom, and a final comparative analysis of the four classrooms. Four predominant themes of social interaction (resistance, conformism, accommodation, and negotiation) emerged with terminology adapted from Giroux’s (2001) theory of resistance in education and Third Space theory (Gutiérrez, 2008). Four types of power (normative, coercive, interactively established contracts, and charm), based on Carspecken’s (1996) typology, were found in the interactions between teacher and students in varying degrees for different purposes. This research contributes to the knowledge base on teacher-student classroom interactions, specifically in relation to exclusionary discipline. Understanding how the themes and varying power relations influence their decisions and actions may enable teachers to reduce use of exclusionary discipline and remain focused on positive teacher-student academic interactions.

Multilingualism and conceptual modelling

One of the leading motivations behind the multilingual semantic web is to make resources accessible digitally in an online global multilingual context. Consequently, it is fundamental for knowledge bases to find a way to manage multilingualism and thus be equipped with those procedures for its conceptual modelling. In this context, the goal of this paper is to discuss how common-sense knowledge and cultural knowledge are modelled in a multilingual framework. More particularly, multilingualism and conceptual modelling are dealt with from the perspective of FunGramKB, a lexico-conceptual knowledge base for natural language understanding. This project argues for a clear division between the lexical and the conceptual dimensions of knowledge. Moreover, the conceptual layer is organized into three modules, which result from a strong commitment towards capturing semantic knowledge (Ontology), procedural knowledge (Cognicon) and episodic knowledge (Onomasticon). Cultural mismatches are discussed and formally represented at the three conceptual levels of FunGramKB.

Um modelo de suporte à comunicação de agentes para tratamento de informação imprecisa baseada em sinônimos

Este trabalho propõe o desenvolvimento de um modelo de suporte á comunicação entre agentes e uma Ontologia com informações imprecisas. Os conceitos desta ontologia podem possuir sinônimos possibilitando a interpretação de termos linguísticos imprecisos. Tal problema é relacionado às questões de desenvolvimento da comunicação em Sistemas Multiagentes, possuindo como referência uma base de conhecimento da qual estes agentes possam requisitar informações. Neste estudo, a premissa do modelo é o de ser útil como componente na utilização por desenvolvedores que queiram utilizar de forma simplificada uma conexão com uma Ontologia para dar suporte na comunicação. Para o presente estudo são discutidos os conceitos sobre a comunicação no ambiente multiagentes. Também é realizada uma revisão sobre o desenvolvimento de Ontologias, de forma a criar uma ontologia para os agentes. A lógica nebulosa, baseado em variáveis linguísticas, servirá como modeladora da imprecisão da informação, dando suporte a essa questão com a Ontologia e a comunicação. De forma a validar o modelo proposto, é realizado um estudo de caso no sistema multiagentes das hortas urbanas do Parque San Jerónimo, de Sevilha, Espanha.

Probabilistic Models for Scalable Knowledge Graph Construction

In the past decade, systems that extract information from millions of Internet documents have become commonplace. Knowledge graphs -- structured knowledge bases that describe entities, their attributes and the relationships between them -- are a powerful tool for understanding and organizing this vast amount of information. However, a significant obstacle to knowledge graph construction is the unreliability of the extracted information, due to noise and ambiguity in the underlying data or errors made by the extraction system and the complexity of reasoning about the dependencies between these noisy extractions. My dissertation addresses these challenges by exploiting the interdependencies between facts to improve the quality of the knowledge graph in a scalable framework. I introduce a new approach called knowledge graph identification (KGI), which resolves the entities, attributes and relationships in the knowledge graph by incorporating uncertain extractions from multiple sources, entity co-references, and ontological constraints. I define a probability distribution over possible knowledge graphs and infer the most probable knowledge graph using a combination of probabilistic and logical reasoning. Such probabilistic models are frequently dismissed due to scalability concerns, but my implementation of KGI maintains tractable performance on large problems through the use of hinge-loss Markov random fields, which have a convex inference objective. This allows the inference of large knowledge graphs using 4M facts and 20M ground constraints in 2 hours. To further scale the solution, I develop a distributed approach to the KGI problem which runs in parallel across multiple machines, reducing inference time by 90%. Finally, I extend my model to the streaming setting, where a knowledge graph is continuously updated by incorporating newly extracted facts. I devise a general approach for approximately updating inference in convex probabilistic models, and quantify the approximation error by defining and bounding inference regret for online models. Together, my work retains the attractive features of probabilistic models while providing the scalability necessary for large-scale knowledge graph construction. These models have been applied on a number of real-world knowledge graph projects, including the NELL project at Carnegie Mellon and the Google Knowledge Graph.