10 results
Search Results
Now showing 1 - 10 of 10
- ItemTemporal Role Annotation for Named Entities(Amsterdam [u.a.] : Elsevier, 2018) Koutraki, Maria; Bakhshandegan-Moghaddam, Farshad; Sack, Harald; Fensel, Anna; de Boer, Victor; Pellegrini, Tassilo; Kiesling, Elmar; Haslhofer, Bernhard; Hollink, Laura; Schindler, AlexanderNatural language understanding tasks are key to extracting structured and semantic information from text. One of the most challenging problems in natural language is ambiguity and resolving such ambiguity based on context including temporal information. This paper, focuses on the task of extracting temporal roles from text, e.g. CEO of an organization or head of a state. A temporal role has a domain, which may resolve to different entities depending on the context and especially on temporal information, e.g. CEO of Microsoft in 2000. We focus on the temporal role extraction, as a precursor for temporal role disambiguation. We propose a structured prediction approach based on Conditional Random Fields (CRF) to annotate temporal roles in text and rely on a rich feature set, which extracts syntactic and semantic information from text. We perform an extensive evaluation of our approach based on two datasets. In the first dataset, we extract nearly 400k instances from Wikipedia through distant supervision, whereas in the second dataset, a manually curated ground-truth consisting of 200 instances is extracted from a sample of The New York Times (NYT) articles. Last, the proposed approach is compared against baselines where significant improvements are shown for both datasets.
- ItemSemSur: A Core Ontology for the Semantic Representation of Research Findings(Amsterdam [u.a.] : Elsevier, 2018) Fathalla, Said; Vahdati, Sahar; Auer, Sören; Lange, Christoph; Fensel, Anna; de Boer, Victor; Pellegrini, Tassilo; Kiesling, Elmar; Haslhofer, Bernhard; Hollink, Laura; Schindler, AlexanderThe way how research is communicated using text publications has not changed much over the past decades. We have the vision that ultimately researchers will work on a common structured knowledge base comprising comprehensive semantic and machine-comprehensible descriptions of their research, thus making research contributions more transparent and comparable. We present the SemSur ontology for semantically capturing the information commonly found in survey and review articles. SemSur is able to represent scientific results and to publish them in a comprehensive knowledge graph, which provides an efficient overview of a research field, and to compare research findings with related works in a structured way, thus saving researchers a significant amount of time and effort. The new release of SemSur covers more domains, defines better alignment with external ontologies and rules for eliciting implicit knowledge. We discuss possible applications and present an evaluation of our approach with the retrospective, exemplary semantification of a survey. We demonstrate the utility of the SemSur ontology to answer queries about the different research contributions covered by the survey. SemSur is currently used and maintained at OpenResearch.org.
- ItemIn Search of Determinism-Sensitive Region to Avoid Artefacts in Recurrence Plots(Singapore [u.a.] : World Scientific Publ. Co., 2018) Wendi, Dadiyorto; Marwan, Norbert; Merz, BrunoAs an effort to reduce parameter uncertainties in constructing recurrence plots, and in particular to avoid potential artefacts, this paper presents a technique to derive artefact-safe region of parameter sets. This technique exploits both deterministic (incl. chaos) and stochastic signal characteristics of recurrence quantification (i.e. diagonal structures). It is useful when the evaluated signal is known to be deterministic. This study focuses on the recurrence plot generated from the reconstructed phase space in order to represent many real application scenarios when not all variables to describe a system are available (data scarcity). The technique involves random shuffling of the original signal to destroy its original deterministic characteristics. Its purpose is to evaluate whether the determinism values of the original and the shuffled signal remain closely together, and therefore suggesting that the recurrence plot might comprise artefacts. The use of such determinism-sensitive region shall be accompanied by standard embedding optimization approaches, e.g. using indices like false nearest neighbor and mutual information, to result in a more reliable recurrence plot parameterization.
- ItemA function space framework for structural total variation regularization with applications in inverse problems(Bristol [u.a.] : Inst., 2018) Hintermüller, Michael; Holler, Martin; Papafitsoros, KostasIn this work, we introduce a function space setting for a wide class of structural/weighted total variation (TV) regularization methods motivated by their applications in inverse problems. In particular, we consider a regularizer that is the appropriate lower semi-continuous envelope (relaxation) of a suitable TV type functional initially defined for sufficiently smooth functions. We study examples where this relaxation can be expressed explicitly, and we also provide refinements for weighted TV for a wide range of weights. Since an integral characterization of the relaxation in function space is, in general, not always available, we show that, for a rather general linear inverse problems setting, instead of the classical Tikhonov regularization problem, one can equivalently solve a saddle-point problem where no a priori knowledge of an explicit formulation of the structural TV functional is needed. In particular, motivated by concrete applications, we deduce corresponding results for linear inverse problems with norm and Poisson log-likelihood data discrepancy terms. Finally, we provide proof-of-concept numerical examples where we solve the saddle-point problem for weighted TV denoising as well as for MR guided PET image reconstruction.
- ItemOntology-Based Representation for Accessible OpenCourseWare Systems(Basel : MDPI Publ., 2018-11-29) Elias, Mirette; Lohmann, Steffen; Auer, SörenOpenCourseWare (OCW) systems have been established to provide open educational resources that are accessible by anyone, including learners with special accessibility needs and preferences. We need to find a formal and interoperable way to describe these preferences in order to use them in OCW systems and retrieve relevant educational resources. This formal representation should use standard accessibility definitions of OCW that can be reused by other OCW systems to represent accessibility concepts. In this article, we present an ontology to represent the accessibility needs of learners with respect to the IMS AfA specifications. The ontology definitions together with rule-based queries are used to retrieve relevant educational resources. Related to this, we developed a user interface component that enables users to create accessibility profiles representing their individual needs and preferences based on our ontology. We evaluated the approach with five examples profiles.
- ItemTracking online topics over time: understanding dynamic hashtag communities(New York, NY [u.a.] : Springer international, 2018) Lorenz-Spreen, Philipp; Wolf, Frederik; Braun, Jonas; Ghoshal, Gourab; Djurdjevac Conrad, Nataša; Hövel, PhilippBackground: Hashtags are widely used for communication in online media. As a condensed version of information, they characterize topics and discussions. For their analysis, we apply methods from network science and propose novel tools for tracing their dynamics in time-dependent data. The observations are characterized by bursty behaviors in the increases and decreases of hashtag usage. These features can be reproduced with a novel model of dynamic rankings. Hashtag communities in time: We build temporal and weighted co-occurrence networks from hashtags. On static snapshots, we infer the community structure using customized methods. On temporal networks, we solve the bipartite matching problem of detected communities at subsequent timesteps by taking into account higher-order memory. This results in a matching protocol that is robust toward temporal fluctuations and instabilities of the static community detection. The proposed methodology is broadly applicable and its outcomes reveal the temporal behavior of online topics. Modeling topic-dynamics: We consider the size of the communities in time as a proxy for online popularity dynamics. We find that the distributions of gains and losses, as well as the interevent times are fat-tailed indicating occasional, but large and sudden changes in the usage of hashtags. Inspired by typical website designs, we propose a stochastic model that incorporates a ranking with respect to a time-dependent prestige score. This causes occasional cascades of rank shift events and reproduces the observations with good agreement. This offers an explanation for the observed dynamics, based on characteristic elements of online media.
- ItemA Computational Pipeline for Sepsis Patients’ Stratification and Diagnosis([Setúbal, Portugal] : SCITEPRESS - Science and Technology Publications, Lda., 2018) Campos, David; Pinho, Renato; Neugebauer, Ute; Popp, Juergen; Oliveira, José Luis; Zwiggelaar, Reyer; Gamboa, Hugo; Fred, Ana; Bermúdez i Badia, SergiSepsis is still a little acknowledged public health issue, despite its increasing incidence and the growing mortality rate. In addition, a clear diagnosis can be lengthy and complicated, due to highly variable symptoms and non-specific criteria, causing the disease to be diagnosed and treated too late. This paper presents the HemoSpec platform, a decision support system which, by collecting and automatically processing data from several acquisition devices, can help in the early diagnosis of sepsis.
- ItemWeb-based access, aggregation, and visualization of future climate projections with emphasis on agricultural assessments(Amsterdam : Elsevier B.V., 2018) Villoria, N.B.; Elliott, J.; Müller, C.; Shin, J.; Zhao, L.; Song, C.Access to climate and spatial datasets by non-specialists is restricted by technical barriers involving hardware, software and data formats. We discuss an open-source online tool that facilitates downloading the climate data from the global circulation models used by the Inter-Sectoral Impacts Model Intercomparison Project. The tool also offers temporal and spatial aggregation capabilities for incorporating future climate scenarios in applications where spatial aggregation is important. We hope that streamlined access to these data facilitates analysis of climate related issues while considering the uncertainties derived from future climate projections and temporal aggregation choices.
- ItemWhy reinvent the wheel: Let's build question answering systems together(New York City : Association for Computing Machinery, 2018) Singh, K.; Radhakrishna, A.S.; Both, A.; Shekarpour, S.; Lytra, I.; Usbeck, R.; Vyas, A.; Khikmatullaev, A.; Punjani, D.; Lange, C.; Vidal, Maria-Esther; Lehmann, J.; Auer, SörenModern question answering (QA) systems need to flexibly integrate a number of components specialised to fulfil specific tasks in a QA pipeline. Key QA tasks include Named Entity Recognition and Disambiguation, Relation Extraction, and Query Building. Since a number of different software components exist that implement different strategies for each of these tasks, it is a major challenge to select and combine the most suitable components into a QA system, given the characteristics of a question. We study this optimisation problem and train classifiers, which take features of a question as input and have the goal of optimising the selection of QA components based on those features. We then devise a greedy algorithm to identify the pipelines that include the suitable components and can effectively answer the given question. We implement this model within Frankenstein, a QA framework able to select QA components and compose QA pipelines. We evaluate the effectiveness of the pipelines generated by Frankenstein using the QALD and LC-QuAD benchmarks. These results not only suggest that Frankenstein precisely solves the QA optimisation problem but also enables the automatic composition of optimised QA pipelines, which outperform the static Baseline QA pipeline. Thanks to this flexible and fully automated pipeline generation process, new QA components can be easily included in Frankenstein, thus improving the performance of the generated pipelines.
- ItemDoMoRe – A recommender system for domain modeling(Setúbal : SciTePress, 2018) Agt-Rickauer, Henning; Kutsche, Ralf-Detlef; Sack, Harald; Hammoudi, Slimane; Ferreira Pires, Luis; Selic, BranDomain modeling is an important activity in early phases of software projects to achieve a shared understanding of the problem field among project participants. Domain models describe concepts and relations of respective application fields using a modeling language and domain-specific terms. Detailed knowledge of the domain as well as expertise in model-driven development is required for software engineers to create these models. This paper describes DoMoRe, a system for automated modeling recommendations to support the domain modeling process. We describe an approach in which modeling benefits from formalized knowledge sources and information extraction from text. The system incorporates a large network of semantically related terms built from natural language data sets integrated with mediator-based knowledge base querying in a single recommender system to provide context-sensitive suggestions of model elements.