Refine
Year of publication
Document Type
- Conference Proceeding (116)
- Doctoral Thesis (14)
- Article (2)
- Book (2)
- Master's Thesis (2)
Language
- English (136) (remove)
Keywords
- Korpus <Linguistik> (29)
- Computerlinguistik (27)
- Computerunterstützte Kommunikation (24)
- Soziale Medien (21)
- Pragmatik (19)
- Linguistik (17)
- Social Media (17)
- NER (13)
- Named entity recognition (13)
- corpus linguistics (11)
Institute
Social media has become an integral part of numerous individuals as well as organizations, with many services being used frequently by a majority of people. Along with its widespread use, the amount of information explodes when people use these services. This demands for efficient tools as well as methods to assist data management and retrieval.
Annotating resources by keywords, known as the tagging task, is a solution to improve categorizability and findability of resources. However, tagging is a human, time-consuming task, which requires the user's focus to figure out many keywords in a short moment and manually enter them into the system. To encourage users to tag their resources more correctly and frequently, tag recommendation is adopted into the social tagging systems to suggest relevant keywords for resources.
In this thesis, we will address the problem of personalized tag recommendation for images and present ways to solve this problem by combining the advantages of the user relation with the images' content. In order to suggest tags for unobserved images, their visual contents are used to replace the index-based information of the image entity in the tagging relations. Because the limitation of low-level features does not show the "content" of images, we propose to utilize a deep learning based approach to learn high-level visual features concurrently with the scoring-tag estimator. For the tag predictor, a latent factor model or a multi-layer perceptron is selected to compute scores of tags by which the top selected tags are sorted in descending order. As a further development upon our findings, we examine the inside and outside context of images to enhance the accuracy of estimators. Regarding the image-inside context, we are motivated by the fact that objects, such as cars or cats are influential on the user's selection criteria. Regarding the image-outside context, the image's surrounding text contributes to the clarity of the image's content for different users. We consider these contextual features as a supporting part which is combined with the mainly visual representation to enhance the tag recommendation performance. Finally, as an additional technique, transfer learning is also adapted to support the proposed models to overcome the limitations of too small training data and boost up their performance. This thesis demonstrates the usefulness and versatility of deep learning approaches for tag recommendation and highlights the importance of the learned image's content in predicting personalized tags. Directions for future work include semantic enhancements to context-based representation and extensions of the content-aware approaches to different recommendation scenarios.
Automating machine learning by providing techniques that autonomously find the best algorithm, hyperparameter configuration and preprocessing is helpful for both researchers and practitioners. Therefore, it is not surprising that automated machine learning has become a very interesting field of research.
Bayesian optimization has proven to be a very successful tool for automated machine learning. In the first part of the thesis we present different approaches to improve Bayesian optimization by means of transfer learning. We present three different ways of considering meta-knowledge in Bayesian optimization, i.e. search space pruning, initialization and transfer surrogate models. Finally, we present a general framework for Bayesian optimization combined with meta-learning and conduct a comparison among existing work on two different meta-data sets. A conclusion is that in particular the meta-target driven approaches provide better results. Choosing algorithm configurations based on the improvement on the meta-knowledge combined with the expected improvement yields best results.
The second part of this thesis is more application-oriented. Bayesian optimization is applied to large data sets and used as a tool to participate in machine learning challenges. We compare its autonomous performance and its performance in combination with a human expert. At two ECML-PKDD Discovery Challenges, we are able to show that automated machine learning outperforms human machine learning experts.
Finally, we present an approach that automates the process of creating an ensemble of several layers, different algorithms and hyperparameter configurations. These kinds of ensembles are jokingly called Frankenstein ensembles and proved their benefit on versatile data sets in many machine learning challenges. We compare our approach Automatic Frankensteining with the current state of the art for automated machine learning on 80 different data sets and can show that it outperforms them on the majority using the same training time. Furthermore, we compare Automatic Frankensteining on a large-scale data set to more than 3,500 machine learning expert teams and are able to outperform more than 3,000 of them within 12 CPU hours.
Number theory is one of the oldest mathematical areas. This is perhaps one of the reasons why there are many connections between number theory and other areas inside mathematics. This thesis is devoted to some of those connections. In the first part of this thesis I describe known connections between number theory and twelve other areas, namely analysis, sequences, applied mathematics (i.e., probability theory and numerical mathematics), topology, graph theory, linear algebra, geometry, algebra, differential geometry, complex analysis, physics and computer science, and algebraic geometry. We will see that the concepts will not only connect number theory with these areas but also yield connections among themselves. In the second part I present some new results in four topics connecting number theory with computer science, graph theory, algebra, and linear algebra and analysis, respectively. [...] In the next topic I determine the neighbourhood of the neighourhood of vertices in some special graphs. This problem can be formulated with generators of subgroups in abelian groups and is a direct generalization of a corresponding result for cyclic groups. In the third chapter I determine the number of solutions of some linear equations over factor rings of principal ideal domains R. In the case R = Z this can be used to bound sums appearing in the circle method. Lastly I investigate the puzzle “Lights Out” as well as variants of it. Of special interest is the question of complete solvability, i.e., those cases in which all starting boards are solvable. I will use various number theoretical tools to give a criterion for complete solvability depending on the board size modulo 30 and show how this puzzle relates to algebraic number theory.
The Oromo people are one of the ancient Kushitic speaking indigenous peoples of Africa. According to linguistic studies, archaeological findings and their Oral history, the original home of the Oromo is believed to be the Nubian Valley of the ancient Kushitic empire. They might have organized themselves as a nation, developed their holistic culture, the gadaa, about 4000 B.C. in their original home, then moved southwards and settled in their current regions as a single independent nation. However, the Abyssinian Emperor Minilik II, who got firearms from some European Christian Kingdoms, colonized the Oromo and built the current Ethiopian empire towards the end of 19th century.
Since then the Oromo lost their independence, were economically marginalized and culturally segregated. Using this situation as an opportunity, the missionaries of Christianity and Islam expanded their religions and established their own religious institutions in Oromia. On one hand, these two new religions brought new cultural elements that could enrich the Oromo culture. On other hand, they destroyed some valuable Oromo cultural heritages preserved by the Oromo Indigenous Religion (OIR). Their mission agents did not carefully consider cultural elements that could have continued. Instead, they destroyed them indiscriminately. The OIR galmaas (worship houses) were destroyed together with Oromo cultural and symbolic objects, and were replaced by Church buildings and mosques.
The Christian missionaries and their local agents assumed the OIR to be idolatry; its feasts, rites, and ritual practices contradictory to the Bible and the Christian faith. Therefore, at the baptismal rite they changed Oromo names to foreign names and discontinued Moggaasaa (OIR child naming rite). Among the Protestant groups of Oromo Christianity (OC), the Oromo’s cultural songs and dances were regarded to be sinful and were therefore abandoned. Oromo cultural foods and drinks were also forbidden.
Against such generalized judgment on the OIR this dissertation raises a question: Are OIR elements contradictory or compatible with the OC? To answer this question, I conducted scientific research, compared OIR and OC elements, and produced this dissertation. This work identifies some identical, similar, partially similar and some differing elements in the two Oromo religions (OIR & OC). It is my hope that these findings might contribute to a religious dialogue that aims to create a peaceful religious coexistence in Oromia and beyond.
Cartel theory, being the doctrine of the cooperation between entrepreneurs of the same industry, was founded in 1883 by the Austrian Friedrich Kleinwächter. This theory, with its specific concepts, was essentially confined to the German-speaking world until World War I. Other cultural or language areas such as the Anglosphere and the Romanic countries had different terminologies and different insights into the topic: There were theories about syndicates, combinations or trusts. The peculiarities of the respective economic cultures hindered a unification of the terms, their meanings and their underlying theories up to the early 1920s. From the mid-1890s, German cartel theory had undergone several conceptual reforms and outdid its foreign-language counterparts in terms of differentiation. Until about 1910, cartel theory (besides American trust theory) had become the most respected theory on economic unions. After World War I, international cartels became needed. Since 1929, the terminology of German cartel theory became fundamental for the corresponding debates, which had taken place first at the International Economic Conference of the League of Nations in 1927. With the entry into the 1930s, the German cartel doctrine had become a scientific standard worldwide. This recognition makes it clear that German economic science was by no means in every respect ‹backward› in the interwar period, which is the current state of research. Therefore, German economics was better prepared than any other national economic discipline for the development of an ever more organized economy as evoked by the extensive cartelization and state-initiated regulation of the 1930s. So, cartel-related expertise was increasingly used in the policy of the controlled economy of the Third Reich.
The water hyacinth (Eichhornia crassipes) is one of the top ten most invasive aquatic plant species in the world. Due to its worldwide distribution, the plant has caused tremendous damage on ecosystems and human livelihoods alike. These negative impacts are especially problematic for developing countries such as Madagascar. Considering the weak economic situation of the country, using water hyacinth to generate economic profits remains the last option to manage the species. We investigated the use of water hyacinth at Lake Alaotra, the largest lake in the country. This lake and the surrounding area are of great ecological and economic relevance for Madagascar. However, the isolation of the region and poverty limit water hyacinth use only to alternatives suitable to the weak local infrastructure. The goal of this research is firstly to identify suitable water hyacinth use options according to the local conditions and to compare them with the locally used raw materials. The first part of this research identified drivers and barriers for using water hyacinth in the region according to the prevailing socioeconomic conditions. It identified especially the use of water hyacinth as raw material for fertilizers and handicrafts as suitable alternatives for Lake Alaotra. Within the second phase, water hyacinth handicrafts were produced and compared with the predominantly used traditional papyrus handicrafts regarding production path and related costs. It was found that assembling water hyacinth handicrafts was easier and faster and they could be sold at three times the sale prices of the traditional papyrus handicrafts. Within the last part, fertilizers based on water hyacinth (composts, green manure and ash) were locally produced and compared with the commonly used agricultural fertilizers NPK and cow dung. This was done by conducting a growth experiment with Chinese cabbage, a common fast-growing vegetable in the region. Additionally, the production and transportation costs of each type of fertilizer were also taken into account. The results showed high biomass gain of cabbage grown with water hyacinth composts which was also proved be cheaper than using NPK and cow dung. All in all, this research demonstrated the efficiency of water hyacinth use as compost and handicraft as a new source of income for the Alaotra region. However, the poverty and high vulnerability of the local population must be considered along the process for a successful implementation of water hyacinth use at Lake Alaotra. A participatory approach and by offering financial insurance to the farmers during the implementation phase could encourage them to test water hyacinth compost on their own fields. Due to the various external factors influencing the marketing of water hyacinth handicrafts, an intensive and sustained supervision should be provided to the craftswomen.
This work is rooted in the fields of English Literary Studies, Cultural Studies, and Jewish American Studies. It examines memory representation in exemplary works published around the millennial change by third generation Jewish American writers Jonathan Safran Foer, Shalom Auslander, and Nicole Krauss. The focus lies on the latter’s work. Symbolic characters and objects connected to memory are discerned and analyzed in detail.
In this thesis we design and test Learning Analytics algorithms for personalized tasks' sequencing that suggests the next task to a student according to his/her specific needs. Our solution is based on a sequencing policy derived from the Vygotsky's Zone of Proximal Development (ZPD), which denes those tasks that are neither too easy not too dicult for the student. The sequencer, called Vygotsky Policy Sequencer (VPS), can identify tasks in the ZPD thanks to the information it receives from performance prediction algorithms able to estimate
the knowledge of the student.
Under this context we describe hereafter the thesis contributions.
(1) A feasibility evaluation of domain independent Matrix Factorization applied in ITS for Performance Prediction.
(2) An adaption and the related evaluation of a domain independent update for online learning Matrix Factorization in ITS.
(3) A novel Matrix Factorization update method based on Kalman Filters approach. Two different updating functions are used: (a) a simple one considering the task just seen, and (b) one able to derive the skills' deficiency of the student.
(4) A new method for offline testing of machine learning controlled sequencers by modeling simulated environment composed by a simulated students and tasks with continuous knowledge and score
representation and different diffculty levels.
(5) The design of a minimal invasive API for the lightweight integration of machine learning components in larger systems to minimize the risk of integration and the cost of expertise transfer.
Profiting from all these contributions, the VPS was integrated in a commercial system and evaluated with 100 children over a month.
The VPS showed comparable learning gains and perceived experience results with those of the ITS sequencer. Finally, thanks to its better modeling abilities, the students finish faster the assigned tasks.
Cultural managers are increasingly engaged ininternational projects; they work in international art festivals, globalcompanies of the creative industries, or international tourism. They areinvolved in cultural diplomacy and cultural development cooperation; andmoreover, in times of an increasing worldwide migration, cultural managers areengaged in moderating “intercultural” change management processes in their owncountries.
How is internationalization influencingcultural management? Is there a tendency towards harmonization of managementpractices due to cultural globalization?
How do cultural managers from different worldregions describe their working conditions also in terms of cultural policy, andwhich differences can be observed?
What are the main challenges of internationalcultural cooperation, which competencies are needed for working ininternational and intercultural contexts, and which training concepts ininternational cultural management proved to be successful?
These questions are investigated on the basisof a world wide survey of cultural managers.
The acquisition of grammatical gender by multilingual pre-school children (aged six) was investigated by observing their narration and discourse. It emerged that only three of the 17 children actually used gender to classify nouns. Grammatical agreement is acknowledged as a key feature of gender acquisition, and it reflects developmental steps. Children growing up with mostly bilingual German input at a low proficiency level had the greatest difficulties in acquiring gender and agreement in the group investigated.
