The way people acquire knowledge has largely shifted from print to web resources. Meanwhile, search has become the main medium to access information. Amongst various search behaviors, exploratory search represents a learning process that involves complex cognitive activities and knowledge acquisition. Research on exploratory search studies on how to make search systems help people seek information and develop intellectual skills. This research focuses on information retrieval and aims to build an exploratory search system that shows higher clustering performance and diversified search results. In this study, a new language model that integrates the state-of-the-art vector language model (i.e., BERT) with human knowledge is built to better understand and organize search results. The clustering performance of the new model (i.e., RDF+BERT) was similar to the original model but slight improvement was observed with conversational texts compared to the pre-trained language model and an exploratory search baseline. With the addition of the enrichment phase of expanding search results to related documents, the novel system also can display more diverse search results.

<p>Graphs are the natural framework of many of today’s highest impact computing applications: from online social networking, to Web search, to product recommendations, to chemistry, to bioinformatics, to knowledge bases, to mobile ad-hoc networking. To develop successful applications in these domains, we often need representation learning methods ---models mapping nodes, edges, subgraphs or entire graphs to some meaningful vector space. Such models are studied in the machine learning subfield of graph representation learning (GRL). Previous GRL research has focused on learning node or entire graph representations through associational tasks. In this work I study higher-order (k>1-node) representations of graphs in the context of both associational and counterfactual tasks.<br> </p>

No description available.

Goal of this master's thesis was in cooperation with the company Avast to design a system, which can extract knowledge from a database of graphs. Graphs, used for data mining, describe behaviour of computer systems and they are anonymously inserted into the company's database from systems of the company's products users. Each graph in the database can be assigned with one of two labels: clean or malware (malicious) graph. The task of the proposed self-learning system is to find clusters of graphs in the graph database, in which the classes of graphs do not mix. Graph clusters with only one class of graphs can be interpreted as different types of clean or malware graphs and they are a useful source of further analysis on the graphs. To evaluate the quality of the clusters, a custom metric, named as monochromaticity, was designed. The metric evaluates the quality of the clusters based on how much clean and malware graphs are mixed in the clusters. The best results of the metric were obtained when vector representations of graphs were created by a deep learning model (variational  graph autoencoder with two relation graph convolution operators) and the parameterless method MeanShift was used for clustering over vectors.

The area of Knowledge Graphs has grown significantly during recent time and has found many different applications both in industrial and academic settings. Despite this, many large Knowledge Graphs are in fact incomplete, which leads to the problem of finding the missing facts in the graphs using Link Prediction. There are several ways of performing Link prediction, the most common one that has emerged recently being using Machine learning techniques to learn low-dimensional representations of the Knowledge Graph called Knowledge Graph embeddings. This project attempts to explore whether or not this is a viable method to use in order to give suggestions for companies that want to expand their businesses. In order to test this hypothesis, a Knowledge Graph was built using real company data from open sources. Then different Knowledge Graph embedding models were trained on the data in order to predict missing elements in the Knowledge Graph. The models were then compared to see which one is most suitable for this task and data set. The geometric based models were found to perform the best for the specific data set used in this project. In this category there are models such as TransE, TransR and RotatE. The results point to the method being a valid option for giving expansion suggestions to companies using a Knowledge Graph of other companies and their products. However, to be certain of this, further research needs to be done where the method needs to be implemented on a larger scale using more diverse data. / Området kunskapsgrafer har växt mycket under de senaste åren och har många olika tillämpningar både inom akademiska och industriella områden. Trots denna tillväxt så är många kunskapsgrafer ofullständiga, vilket leder till problemet att hitta den faktan i kunskapsgraferna som saknas genom något som kallas länkförutsägelser. Det finns många olika metoder för att göra länkförutägelser, men den populäraste metoden som uppkommit de senaste åren är att använda maskininlärning för att lära in lågdimensionerade representationer av kunskapsgrafen i något som kallas kunskapsgrafsinbäddningar. I det här projektet försöker vi ta reda på om den här metoden går att använda för att ge förslag för företag som vill expandera och etablera sig på nya marknader. För att testa om detta är möjligt byggdes en kunskapsgraf med hjälp av data från öppna källor. Sedan fick olika kunskapsgrafsinbäddningsmodeller träna på data från kunskapsgrafen för att sedan kunna hitta fakta i grafen som saknades. De olika modellerna jämfördes sedan för att se vilken som var mest lämplig för att klara av uppgiften på vår kunskapsgraf. De modeller som är geometribaserade visade sig prestera bäst, bland dom fanns modeller som TransE, TransR och RotatE. Resultaten från projektet visar på att metoden är användbar för uppgiften att ge förslag om områden som ett företag kan expandera till. Dock skulle detta behöva undersökas mer med en större mer mångfaldig mängd data för att vara säker på att detta går att använda i fler marknadsområden än dem som ingick i projektet.