Results 41-60 of 90.
Bookmark and Share    
Full Text
See detailProceedings International Workshop Exploring Old Maps 2016
van Dijk, Thomas; Schommer, Christoph UL

Book published by University of Luxembourg (2016)

Many libraries own an extensive collection of historical maps. Beside their value as historical objects, these maps are an important source of information for researchers in various scientific disciplines ... [more ▼]

Many libraries own an extensive collection of historical maps. Beside their value as historical objects, these maps are an important source of information for researchers in various scientific disciplines. This ranges from the actual history of cartography and general history to the geographic and social sciences. With the progressing digitisation of libraries and archives, these maps become more easily available to a larger public. A basic level of digitisation consists of scanned bitmap images, tagged with some basic bibliographic information such as title, author and year of production. In order to make the maps more accessible, further metadata describing the contained information is desirable. This would enable more user-friendly interfaces, relevant queries of a database, and automatic analyses. The International Workshop on Exploring Old Maps provides a forum for the communication of results that may be useful to the community. Researchers and practitioners of many areas working on unlocking the content of old maps have contributed to this year’s program - humanities scholars, developers, computer and information scientists as well as librarians, archivists and curators. [less ▲]

Detailed reference viewed: 129 (11 UL)
Full Text
Peer Reviewed
See detailRAT: A Referencing and Annotation Tool for Digitized Early Maps
Höhn, Winfried UL; Schommer, Christoph UL

Scientific Conference (2016, June)

RAT is designed to support users in identifying place markers in digitised early maps and to link these place markers to modern maps. RAT facilitates a geo-referencing by suggesting the most likely modern ... [more ▼]

RAT is designed to support users in identifying place markers in digitised early maps and to link these place markers to modern maps. RAT facilitates a geo-referencing by suggesting the most likely modern places based on an estimated mapping and a phonetic search for place names. [less ▲]

Detailed reference viewed: 151 (12 UL)
Full Text
Peer Reviewed
See detailInteraction Profiles for an Artificial Conversational Companion
Höhn, Sviatlana UL; Busemann, Stephan; Max, Charles UL et al

Scientific Conference (2015, September)

Using Artificial Companions for tasks requiring long-term interaction like language learning or coaching can be approached by creating local computational models for particular interaction structures, and ... [more ▼]

Using Artificial Companions for tasks requiring long-term interaction like language learning or coaching can be approached by creating local computational models for particular interaction structures, and models reflecting changes in interaction over time. An Artificial Conversational Companion (ACC) that helps to practice conversation in a foreign language is expected to play the role of a language expert in conversation. We apply methods of Conversation Analysis to obtain data- driven models of interaction profiles for language experts and language novices from a corpus of instant messaging based dialogues between native speakers of German and advanced learners of German as a foreign language. We show different ways how the artificial agent can simulate ”doing being expert” in conversation and promote learning. [less ▲]

Detailed reference viewed: 297 (46 UL)
Full Text
See detailSentiment Barometer in Financial News
Schommer, Christoph UL

Report (2014)

This booklet is a collection of project reports written by graduate students, who have participated the course "Machine Learning" in Winter Term 2013/14. Here, we have concerned Financial News Documents ... [more ▼]

This booklet is a collection of project reports written by graduate students, who have participated the course "Machine Learning" in Winter Term 2013/14. Here, we have concerned Financial News Documents regarding the Irish Financial Crisis in the years of 2009 - 2013. We have studied different forms of sentiments, for example with StoryTakes, Alerts, Headlines, authors, and others. [less ▲]

Detailed reference viewed: 150 (12 UL)
Full Text
Peer Reviewed
See detailFinding Outliers in Satellite Patterns by Learning Pattern Identities
Bouleau, Fabien; Schommer, Christoph UL

in Filipe, Joacquim; Fred, Ana (Eds.) Proceedings "6th International Conference on Agents an Artificial Intelligence" (2014, January)

Spacecrafts provide a large set of on-board components information such as their temperature, power and pressure. This information is constantly monitored by engineers, who capture the outliers and ... [more ▼]

Spacecrafts provide a large set of on-board components information such as their temperature, power and pressure. This information is constantly monitored by engineers, who capture the outliers and determine whether the situation is abnormal or not. However, due to the large quantity of information, only a small part of the data is being processed or used to perform anomaly prediction. A common accepted research concept for anomaly prediction as described in literature yields on using projections, based on probabilities, estimated on learned patterns from the past (Fujimaki et al., 2005) and data mining methods to enhance the conventional diagnosis approach (Li et al., 2010). Most of them conclude on the need to build a status vector. We propose an algorithm for efficient outlier detection that builds an identity chart of the patterns using the past data based on their curve fitting information. It detects the functional units of the patterns without apriori knowledge with the intent to learn its structure and to reconstruct the sequence of events described by the signal. On top of statistical elements, each pattern is allotted a characteristics chart. This pattern identity enables fast pattern matching across the data. The extracted features allow classification with regular clustering methods like support vector machines (SVM). The algorithm has been tested and evaluated using real satellite telemetry data. The outcome and performance show promising results for faster anomaly prediction. [less ▲]

Detailed reference viewed: 290 (18 UL)
Full Text
Peer Reviewed
See detailA Hidden Markov Model to detect relevance in nancial documents based on on/off topics
Kampas, Dimitrios UL; Schommer, Christoph UL; Sorger, Ulrich UL

in European Conference on Data Analysis (2014)

Automated text classification has gained a significant attention since a vast amount of documents in digital forms are widespread and continuously increasing. Most of the standard classification posit the ... [more ▼]

Automated text classification has gained a significant attention since a vast amount of documents in digital forms are widespread and continuously increasing. Most of the standard classification posit the independence of the terms-features in document, which is unrealistic considering the sophisticated structure of the language. Our research concerns the discovery of relevance in documents, which adequately refers to a sufficient number of thematic themes (or topics) that are either `on' or `off'. `On topics' are semantically close with a domain specific discourse, whereas `Off topics' are not considered to be on documents. As a rather promising approach, we have modelled a stochastic process for term sequences, where each term is conditionally dependent of its preceeding terms. Hidden Markov Models hereby provide a reliable potential to incorporate language and domain dependencies for a classification. Terms are deterministically associated with classes to improve the probability estimates for the infrequent words. In the paper presentation, we demonstrate our approach and motivate its eligibility by the exploration of annotated Thomson Reuters news documents; in particular, the `on topic' documents discourse the monetary policy of Federal Reserves. We estimate the transition and emission probabilities of our model on a training set of both on and off topic documents and evaluate the accuracy of our approach using 10-fold cross validation. This work is part of the interdisciplinary research project ESCAPE, which is funded by the Fonds National de la Recherche. We kindly thank our colleagues from the Dept. of Finance for their support. [less ▲]

Detailed reference viewed: 317 (57 UL)
Full Text
Peer Reviewed
See detailNews Representation with Multi-Word Features
Minev, Mihail UL; Schommer, Christoph UL

in Proceedings ECDA (2013, July)

Detailed reference viewed: 79 (20 UL)
Full Text
Peer Reviewed
See detailDomain-driven news representation using conditional attribute-value pairs
Minev, Mihail UL; Schommer, Christoph UL

in Ferro, Nicola (Ed.) PROMISE Winter School 2013: Bridging between Information Retrieval and Databases (2013)

Detailed reference viewed: 125 (14 UL)
Full Text
Peer Reviewed
See detailOutlier Identification in Spacecraft Monitoring Data using Curve Fitting Information
Bouleau, Fabien; Schommer, Christoph UL

in Proceedings ECDA (2013)

Detailed reference viewed: 125 (8 UL)
Full Text
Peer Reviewed
See detailTowards Computational Models for a Long-term Interaction with an Artificial Conversational Companion
Danilava, Sviatlana UL; Busemann, Stephan; Schommer, Christoph UL et al

in Proceedings "5th International Conference on Agents an Artificial Intelligence" (2013)

Detailed reference viewed: 228 (14 UL)
Full Text
Peer Reviewed
See detailWhy are you Silent? - Towards Responsiveness in Chatbots
Danilava, Sviatlana UL; Busemann, Stephan; Schommer, Christoph UL et al

in Avec le Temps! Time, Tempo, and Turns in Human-Computer Interaction". Workshop at CHI 2013, Paris, France (2013)

In this position paper we consider temporal phenomena in interaction with text-based conversational agents. In particular, we focus on two dimensions of time in instant messaging dialogues: responsiveness ... [more ▼]

In this position paper we consider temporal phenomena in interaction with text-based conversational agents. In particular, we focus on two dimensions of time in instant messaging dialogues: responsiveness as a measure for interaction placed in time, and interaction management performed by interaction participants caused by partner's exceeding of the maximum expected responsiveness. [less ▲]

Detailed reference viewed: 365 (16 UL)
Full Text
See detailNews and stock markets: A survey on abnormal returns and prediction models
Minev, Mihail UL; Schommer, Christoph UL; Grammatikos, Theoharry UL

Report (2012)

Vast amount of news articles are published daily reflecting global topics. The stories represent information about events and expert opinions, which may trigger positive or negative expectations on the ... [more ▼]

Vast amount of news articles are published daily reflecting global topics. The stories represent information about events and expert opinions, which may trigger positive or negative expectations on the stock markets. The literature describes various methods for analyzing such correlations. In this paper we consider related approaches for tracking the impact of news on abnormal stock returns. In the first part we introduce studies with back- ground in Finance. Primarily by applying statistical functions the works examine unusual price volatilities and explore possible sources and market conditions, e.g. biased investors, limited attention, macro-economic variables, country development state, et cetera. In the second part we present studies with background in Computer Science, which take advan- tage of historic news and the equivalent market values. By following the common learning paradigm the projects elaborate prototypes for trend and stock price prediction. In the current survey we evaluate leading approaches regarding the objectives, assumptions, in- put, techniques, and performance. Moreover we provide a comparison framework of the recent prototypes and identify gaps for future research. [less ▲]

Detailed reference viewed: 670 (20 UL)
Full Text
Peer Reviewed
See detailOperations on Conversational Mind-Graphs
Poray, Jayanta UL; Schommer, Christoph UL

in Proceedings "4th International Conference on Agents and Artificial Intelligence" (2012)

Detailed reference viewed: 126 (7 UL)
Peer Reviewed
See detailLong-term Human-machine Interaction: Organisation and Adaptability of Talk-in-interaction
Danilava, Sviatlana UL; Schommer, Christoph UL; Ziegler, Gudrun UL

in CHIST-ERA Conference, Edinburgh, Scotland. (2012)

Detailed reference viewed: 109 (13 UL)
Full Text
Peer Reviewed
See detailArtificial Conversational Companions A Requirements Analysis
Danilava, Sviatlana UL; Busemann, Stephan; Schommer, Christoph UL

in Proceedings "4th International Conference on Agents and Artificial Intelligence" (2012)

This paper is based on several attempts to provide a definition of an Artificial Companion that can be found in the referenced literature. Although accepted by the research community, such descriptions ... [more ▼]

This paper is based on several attempts to provide a definition of an Artificial Companion that can be found in the referenced literature. Although accepted by the research community, such descriptions set very high expectations of such agents, but they do not address the technical feasibility and the system limitations, that is why they need an elaborated and precise explanation. In this paper, we focus on computer agents that simulate human language behaviour, and are aimed to serve, to assist and to accompany their owner over a long period of time, that we call Artificial Conversational Companions. This is the first approach to analyse the effort required to meet the expectations of Artificial Conversational Companion and discuss the identified design issues. [less ▲]

Detailed reference viewed: 402 (10 UL)
Full Text
Peer Reviewed
See detailA Molecular Concept of Managing Data
Schommer, Christoph UL

in Abstract book of 2nd Conference on Agents and Artificial Intelligence (ICAART 2010) (2010)

The following (position) paper follows the concept of the field of Artificial Life and argues that the (relational) management of data can be understood as a chemical model. Whereas each data itself is ... [more ▼]

The following (position) paper follows the concept of the field of Artificial Life and argues that the (relational) management of data can be understood as a chemical model. Whereas each data itself is consistent with atomic entities, each combination of data corresponds to a (artificial) molecular structure. For example, an attribute D inside a relational system can be represented by a nucleus aD sharing a cloud of values, which consists of so-called valectrons (the values for the column D). By using reaction rules like the selection of tuples or projection of attributes, a retrieve of molecules can be achieved quite easily. Advantages of the chemical model are no data types, a fast data access, and the associative nature of the molecules: this automatically supports a direct identification of patterns in the sense of data mining. A disadvantage is the need for restructuring that must eventually be done, because the incoming data stream is allowed to influence the chemical model. With this position paper, we present our basic concept. [less ▲]

Detailed reference viewed: 99 (5 UL)
Full Text
Peer Reviewed
See detailTowards E-Conviviality in Web-Based Systems by considering the Wisdom of Crowds
Kaufmann, Sascha UL; Schommer, Christoph UL

in Abstract book of 2nd Conference on Agents and Artificial Intelligence (ICAART 2010) (2010)

Detailed reference viewed: 54 (7 UL)