Labeling of Symbolic Prosody Breaks for the Slovenian Language

This paper presents the data-driven prediction of word level prosody breaks modelling for the Slovenian language. Automatic learning techniques depend on the construction of a large corpus labeled appropriately. This labeling can be done either automatically, or by hand. While automatic labeling can be less accurate than hand labeling, the latter is very time consuming and, in some cases, inconsistent. Therefore, a new interactive tool for word level prosody labeling (major/minor breaks) is presented together with a new semi-automatic approach for determining prosody breaks. This interactive tool combines the advantages of hand labeling and automatic labeling by achieving a high consistency in labeling and reducing the time needed for hand labeling. The labeled Slovenian corpus has been used to train our phrase break prediction module, implementing a neural network (NN) structure. Experiments for the data-driven prediction of major = minor and major/minor phrase breaks were performed. The prediction accuracy achieved marks state-of-the-art word level prosody breaks prediction for the Slovenian language and is comparable to the prediction accuracy of other approaches in which more complex NN structures (Müller et al., 2000) or other prediction methods (Black and Tailor, 1997) were applied, and a much larger corpus was used for training. The overall prediction accuracy achieved is 94% for major = minor breaks and over 98/92% for major/minor phrase breaks, respectively.     

Mechanical,thermal, and burning properties of viscose fabric composites: Influence of epoxy resin modification

The influence of epoxy resin modification by 3‐aminopropyltriethoxysilane (APTES) on various properties of warp knitted viscose fabric is reported in this study. Dynamic mechanical, impact resistance, flexural, thermal properties, and burning behavior of the epoxy/viscose fabric composites are studied with respect to varying content of silane coupling agent. The results obtained for APTES‐modified epoxy resin based composites reinforced with unmodified viscose fabric composites are compared to unmodified epoxy resin based composites reinforced with APTES‐modified viscose fabric. The dynamic mechanical behavior of the APTES‐modified resin based composites indicates improved interfacial adhesion. The composites prepared from modified epoxy resin exhibited a twofold increase in impact resistance. The improved adhesion between the fiber and modified resin was also visible from the scanning electron microscope analysis of the impact fracture surface. There was less influence of resin modification on the flexural properties of the composites. The 5% APTES modification induced early degradation of composites compared to all other composites. The burning rate of all the composites under study is rated to be satisfactory for use in automotive interior applications. © 2018 Wiley Periodicals, Inc. J. Appl. Polym. Sci. 2018 , 135, 46673.     

Annotated news corpora and a lexicon for sentiment analysis in Slovene

In this study, we introduce Slovene web-crawled news corpora with sentiment annotation on three levels of granularity: sentence, paragraph and document levels. We describe the methodology and tools that were required for their construction. The corpora contain more than 250,000 documents with political, business, economic and financial content from five Slovene media resources on the web. More than 10,000 of them were manually annotated as negative, neutral or positive. All corpora are publicly available under a Creative Commons copyright license. We used the annotated documents to construct a Slovene sentiment lexicon, which is the first of its kind for Slovene, and to assess the sentiment classification approaches used. The constructed corpora were also utilised to monitor within-the-document sentiment dynamics, its changes over time and relations with news topics. We show that sentiment is, on average, more explicit at the beginning of documents, and it loses sharpness towards the end of documents.     

Deep node ranking for neuro-symbolic structural node embedding and classification

Network node embedding is an active research subfield of complex network analysis. This paper contributes a novel approach to learning network node embeddings and direct node classification using a node ranking scheme, coupled with an autoencoder-based neural network architecture. The main advantages of the proposed Deep Node Ranking (DNR) algorithm are competitive or better classification performance, significantly higher learning speed and lower space requirements when compared to state-of-the-art approaches on 15 real-life structural node classification benchmarks. It also enables exploration of the relationship between symbolic and the derived sub-symbolic node representations, offering insights into the learned node space structure. To avoid the space complexity bottleneck in a direct node classification setting, DNR, if needed, computes stationary distributions of personalized random walks from given nodes in mini-batches, scaling seamlessly to larger networks. The scaling laws associated with DNR were also investigated by considering 1,488 synthetic Erd?s-Rényi networks, demonstrating its scalability to tens of millions of links.     

液相合成甲醇催化剂活性的研究

The effects of reduction procedure, reaction temperature and composition of feed gas on the activity of a CuO-ZnO-Al2O3 catalyst for liquid phase methanol synthesis were studied. An optimized procedure different from conventional ones was developed to obtain higher activity and better stability of the catalyst. Both CO and CO2 in the feed gas were found to be necessary to maintain the activity of catalyst in the synthesis process. Reaction temperature was limited up to 523K, otherwise the catalyst will be deactivated rapidly. Experimental results show that the catalyst deactivation is caused by sintering and fouling, and the effects of CO and CO2 on the catalyst activity are also investigated. The experimental results indicate that the formation of water in the methanol synthesis is negligible when the feed gas contains both CO and CO2. The mechanism for liquid-phase methanol synthesis was discussed and it differed slightly from that for gas-phase synthesis.     

Computer-aided analysis of the forging process

This paper presents computer simulation of the forging process using the finite volume method (FVM). The process of forging is highly non-linear, where both large deformations and continuously changing boundary conditions occur. In most practical cases, the initial billet shape is relatively simple, but the final shape of the end product is often geometrically complex, to the extent that it is commonly obtained using multiple forming stages.Examples of the numerical simulation of the forged pieces provided were created using Msc/SuperForge computer code. The main results of the analysis are deformed shape, temperature, pressure, effective plastic strain, effective stress and forces acting on the die.Nomenclature C material constant - M strain rate hardening exponent - N strain hardening exponent - S coefficient of the microstructure - T temperature - u _i velocity component - x _j Cartesian coordinates - ̄ effective strain tensor - effective strain rate - ̇ proportionality factor in flow rules - _ij Cauchy stress tensor - _i deviator stress tensor - ̄ effective stress tensor - _y flow stress     

Analysis of Slovenian research community through bibliographic networks

Science is a societal process, designed on widely accepted general rules which facilitate its development. Productive researchers are viewed from the perspective of a social network of their interpersonal relations. In this paper we address performance of Slovenian research community using bibliographic networks between the years 1970 and 2015 from various aspects which determine prolific science. We focus on basic determinants of research performance including productivity, collaboration, internationality, and interdisciplinarity. For each of the determinants, we select a set of statistics and network measures to investigate the state of each in every year of the analyzed period. The analysis is based on high quality data from manually curated information systems. We interpret the results by relating them to important historical events impacting Slovenia and to domestic expenditure for research and development. Our results clearly demonstrate causal relations between the performance of research community and changes in wider society. Political and financial stability together with concise measuring of scientific productivity established soon after Slovenia won independence from Yugoslavia in 1991 had positive influence on all determinants. They were further leveraged by foundation of Slovenian research agency and joining EU and NATO. Publish and perish phenomenon, negative impacts of financial crisis in 2008–2014 and reshaping the domestic expenditure for research and development after 2008 have also clear response in scientific community. In the paper, we also study the researcher’s career productivity cycles and present the analysis of the career productivity for all registered researchers in Slovenia.     

The interprocess NIR sampling as an alternative approach to multivariate statistical process control for identifying sources of product-quality variability

We are presenting a new approach of identifying sources of variability within a manufacturing process by NIR measurements of samples of intermediate material after each consecutive unit operation (interprocess NIR sampling technique). In addition, we summarize the development of a multivariate statistical process control (MSPC) model for the production of enteric-coated pellet product of the proton-pump inhibitor class. By developing provisional NIR calibration models, the identification of critical process points yields comparable results to the established MSPC modeling procedure. Both approaches are shown to lead to the same conclusion, identifying parameters of extrusion/spheronization and characteristics of lactose that have the greatest influence on the end-product’s enteric coating performance. The proposed approach enables quicker and easier identification of variability sources during manufacturing process, especially in cases when historical process data is not straightforwardly available. In the presented case the changes of lactose characteristics are influencing the performance of the extrusion/spheronization process step. The pellet cores produced by using one (considered as less suitable) lactose source were on average larger and more fragile, leading to consequent breakage of the cores during subsequent fluid bed operations. These results were confirmed by additional experimental analyses illuminating the underlying mechanism of fracture of oblong pellets during the pellet coating process leading to compromised film coating.