scholarly journals Enhanced Language Model with Hybrid Knowledge Graph for Mathematical Topic Prediction

2021 ◽  
Author(s):  
Minghui Wu ◽  
Canghong Jin ◽  
Wenkang Hu ◽  
Yabo Chen
Keyword(s):  
Language Model ◽  
Real Data ◽  
Mathematical Concept ◽  
Fine Tuning ◽  
Knowledge Graph ◽  
Mathematics Knowledge ◽  
Hybrid Knowledge ◽  
Model Set ◽  
Set Up ◽  
Mathematical Topic

Understanding mathematical topics is important for both educators and students to capture latent concepts of questions, evaluate study performance, and recommend content in online learning systems. Compared to traditional text classification, mathematical topic classification has several main challenges: (1) the length of mathematical questions is relatively short; (2) there are various representations of the same mathematical concept(i.e., calculations and application); (3) the content of question is complex including algebra, geometry, and calculus. In order to overcome these problems, we propose a framework that combines content tokens and mathematical knowledge concepts in whole procedures. We embed entities from mathematics knowledge graphs, integrate entities into tokens in a masked language model, set up semantic similarity-based tasks for next-sentence prediction, and fuse knowledge vectors and token vectors during the fine-tuning procedure. We also build a Chinese mathematical topic prediction dataset consisting of more than 70,000 mathematical questions with topics. Our experiments using real data demonstrate that our knowledge graph-based mathematical topic prediction model outperforms other state-of-the-art methods.

scholarly journals Deep Learning-Based Knowledge Graph Generation for COVID-19

2021 ◽  
Vol 13 (4) ◽  
pp. 2276
Author(s):  
Taejin Kim ◽  
Yeoil Yun ◽  
Namgyu Kim
Keyword(s):  
Knowledge Base ◽  
Language Model ◽  
Fine Tuning ◽  
Knowledge Graph ◽  
Specific Information ◽  
Specific Knowledge ◽  
Text Documents ◽  
Domain Specific ◽  
Open Information Extraction ◽  
Domain Specific Knowledge

Many attempts have been made to construct new domain-specific knowledge graphs using the existing knowledge base of various domains. However, traditional “dictionary-based” or “supervised” knowledge graph building methods rely on predefined human-annotated resources of entities and their relationships. The cost of creating human-annotated resources is high in terms of both time and effort. This means that relying on human-annotated resources will not allow rapid adaptability in describing new knowledge when domain-specific information is added or updated very frequently, such as with the recent coronavirus disease-19 (COVID-19) pandemic situation. Therefore, in this study, we propose an Open Information Extraction (OpenIE) system based on unsupervised learning without a pre-built dataset. The proposed method obtains knowledge from a vast amount of text documents about COVID-19 rather than a general knowledge base and add this to the existing knowledge graph. First, we constructed a COVID-19 entity dictionary, and then we scraped a large text dataset related to COVID-19. Next, we constructed a COVID-19 perspective language model by fine-tuning the bidirectional encoder representations from transformer (BERT) pre-trained language model. Finally, we defined a new COVID-19-specific knowledge base by extracting connecting words between COVID-19 entities using the BERT self-attention weight from COVID-19 sentences. Experimental results demonstrated that the proposed Co-BERT model outperforms the original BERT in terms of mask prediction accuracy and metric for evaluation of translation with explicit ordering (METEOR) score.

Environmental model studies for the Istanbul master plan. Part I: hydrodynamical design basis and marine disposal of wastewater

1995 ◽  
Vol 32 (2) ◽  
pp. 141-148 ◽  
Author(s):  
I. S. Hansen ◽  
H. J. Vested ◽  
M. A. Latif
Keyword(s):  
Black Sea ◽  
Layer Structure ◽  
The Black Sea ◽  
Marmara Sea ◽  
Junction Area ◽  
3 Dimensional ◽  
Model Studies ◽  
Model Set ◽  
Characteristic Features ◽  
Set Up

A modelling study of the hydrodynamics and spreading of wastewater from existing and future outfalls in the Bosphorus region has been conducted applying a 3-Dimensional model. The modelling is based on SYSTEM 3, which is a general modelling system for baroclinic flow simulating unsteady currents, waterlevels, salinity and temperature within the model area. The model set-up covers the Black Sea-Bosphorus-Marmara Sea junction area. The set-up is calibrated by data from a dedicated field program and previous field experience. The model is designed to describe the characteristic features of the flow in the junction area such as the effects of variations in waterlevel differences between the Sea of Marmara and the Black Sea on the important two-layer structure in the strait and the flow fields generated by the upper layer jet in the Bosphorus-Marmara junction. This model has been applied for evaluation of disposal of wastewater and for the subsequent water quality studies. The general use of a baroclinic 3-D hydrodynamic model to simulate disposal of wastewater is discussed. Examples of the application of the model of the junction area to evaluate the different strategies for disposal of wastewater are presented.

Modelling of impregnation of γ-alumina with cobalt and molybdenum salts. CoCl2-(NH4)2MoO4-γ-Al2O3 (aluminate type) system

1987 ◽  
Vol 52 (3) ◽  
pp. 663-671 ◽  
Author(s):  
Jiří Hanika ◽  
Vladimír Janoušek ◽  
Karel Sporka
Keyword(s):  
Effective Diffusion ◽  
Type System ◽  
Catalyst Particle ◽  
Ammonium Molybdate ◽  
Active Components ◽  
Model Set ◽  
Cobalt Dichloride ◽  
Set Up ◽  
Electron Microanalysis ◽  
Kinetics Of

Adsorption data for the impregnation of alumina with an aqueous solution of cobalt dichloride and ammonium molybdate were treated in terms of the Langmuir adsorption isotherm and compared with a mathematical model set up to describe the kinetics of simultaneous impregnation of a support by two components. The effective diffusion coefficients of the two components at 25 °C in a cylindrical particle of alumina were obtained. The validity of the model used was verified qualitatively by comparing the numerical results with the experimental time dependent concentration profiles of the active components in a catalyst particle, measured by electron microanalysis technique.

scholarly journals Using CFD to Evaluate Natural Ventilation through a 3D Parametric Modeling Approach

Energies ◽  
2021 ◽  
Vol 14 (8) ◽  
pp. 2197
Author(s):  
Nayara Rodrigues Marques Sakiyama ◽  
Jurgen Frick ◽  
Timea Bejat ◽  
Harald Garrecht
Keyword(s):  
Natural Ventilation ◽  
Parametric Modeling ◽  
Cfd Simulations ◽  
3D Design ◽  
Post Process ◽  
Test House ◽  
Model Set ◽  
Computational Fluid Dynamics Cfd ◽  
Set Up ◽  
Passive Strategy

Predicting building air change rates is a challenge for designers seeking to deal with natural ventilation, a more and more popular passive strategy. Among the methods available for this task, computational fluid dynamics (CFD) appears the most compelling, in ascending use. However, CFD simulations require a range of settings and skills that inhibit its wide application. With the primary goal of providing a pragmatic CFD application to promote wind-driven ventilation assessments at the design phase, this paper presents a study that investigates natural ventilation integrating 3D parametric modeling and CFD. From pre- to post-processing, the workflow addresses all simulation steps: geometry and weather definition, including incident wind directions, a model set up, control, results’ edition, and visualization. Both indoor air velocities and air change rates (ACH) were calculated within the procedure, which used a test house and air measurements as a reference. The study explores alternatives in the 3D design platform’s frame to display and compute ACH and parametrically generate surfaces where air velocities are computed. The paper also discusses the effectiveness of the reference building’s natural ventilation by analyzing the CFD outputs. The proposed approach assists the practical use of CFD by designers, providing detailed information about the numerical model, as well as enabling the means to generate the cases, visualize, and post-process the results.

SHOCKS AND FRICTIONS IN THAI ECONOMY: THROUGH THE LENS OF BUSINESS CYCLE ACCOUNTING

2020 ◽  
pp. 1-15
Author(s):  
VIMUT VANITCHAREARNTHUM
Keyword(s):  
Business Cycle ◽  
Open Economy ◽  
Prime Factor ◽  
Aggregate Fluctuations ◽  
Aggregate Output ◽  
Business Cycle Accounting ◽  
Labor Wedge ◽  
Model Set ◽  
Set Up ◽  
Investment Fluctuation

This paper applies business cycle accounting methodology to analyze the sources of aggregate fluctuations in Thai economy, especially during the recent severe recessions in 1997–1998 and 2008–2009. This exploration helps researchers uncover possible shocks and frictions that drive business cycle in a small and open economy within a minimal model set-up. Under this methodology, a fluctuation in aggregate output can be accounted for by exogenous time-varying wedges, namely efficiency wedge, investment wedge, labor wedge, government wedge, etc. This study found that the efficiency wedge is essential in accounting for aggregate output, consumption and investment fluctuation, while the bond wedge, which only present in an open economy setting, is a prime factor in accounting for movement in current accounts. I conducted counterfactual experiments to see what accounts for the output drop during recent recessions. I find that the efficiency wedge played a key role in recent recessions in Thailand, while the investment wedge was accounted for slow economic recovery after the recessions.

Human lung cancer explants model: Set up of a predictive model for treatment

2019 ◽  
Vol 110 ◽  
pp. S28
Author(s):  
B.M.A. Lenoir ◽  
D.S. Ferber ◽  
F. Eichhorn ◽  
M. Eichhorn ◽  
I. Zörnig ◽  
...  
Keyword(s):  
Lung Cancer ◽  
Predictive Model ◽  
Human Lung ◽  
Human Lung Cancer ◽  
Model Set ◽  
Set Up

scholarly journals Projections of runoff in the Vistula and the Odra river basins with the help of the SWAT model

2017 ◽  
Vol 49 (2) ◽  
pp. 303-317 ◽  
Author(s):  
Mikołaj Piniewski ◽  
Mateusz Szcześniak ◽  
Shaochun Huang ◽  
Zbigniew W. Kundzewicz
Keyword(s):  
Assessment Tool ◽  
Statistical Significance ◽  
Swat Model ◽  
Climate Change Impacts ◽  
Odra River ◽  
Assess Climate Change ◽  
Rcp 8.5 ◽  
Model Set ◽  
Seasonal Runoff ◽  
Set Up

Abstract The objective of this paper is to assess climate change impacts on spatiotemporal changes in annual and seasonal runoff and its components in the basins of two large European rivers, the Vistula and the Odra, for future horizons. This study makes use of the Soil and Water Assessment Tool (SWAT) model, set up at high resolution, and driven by a multi-model ensemble (MME) of nine bias-corrected EURO-CORDEX simulations under two representative concentration pathways (RCPs), 4.5 and 8.5. This paper presents a wealth of illustrative material referring to the annual and seasonal runoff (R) in the reference period as well as projections for the future (MME mean change), with explicit illustration of the multi-model spread based on the agreement between models and statistical significance of change according to each model. Annual R increases are dominating, regardless of RCP and future horizon. The magnitude of the MME mean of spatially averaged increase varies between 15.8% (RCP 4.5, near future) and 41.6% (RCP 8.5, far future). The seasonal patterns show the highest increase in winter and the lowest in spring, whereas the spatial patterns show the highest increase in the inner, lowland part, and the lowest in the southern mountainous part of the basin.

scholarly journals Melting and freezing under Antarctic ice shelves from a combination of ice-sheet modelling and observations

2017 ◽  
Vol 63 (240) ◽  
pp. 731-744 ◽  
Author(s):  
JORGE BERNALES ◽  
IRINA ROGOZHINA ◽  
MAIK THOMAS
Keyword(s):  
Mass Balance ◽  
Ice Sheet ◽  
Model Parameters ◽  
Ice Shelf ◽  
Ice Shelves ◽  
Continental Scale ◽  
Model Set ◽  
Set Up ◽  
Basal Melting ◽  
The Antarctic

ABSTRACTIce-shelf basal melting is the largest contributor to the negative mass balance of the Antarctic ice sheet. However, current implementations of ice/ocean interactions in ice-sheet models disagree with the distribution of sub-shelf melt and freezing rates revealed by recent observational studies. Here we present a novel combination of a continental-scale ice flow model and a calibration technique to derive the spatial distribution of basal melting and freezing rates for the whole Antarctic ice-shelf system. The modelled ice-sheet equilibrium state is evaluated against topographic and velocity observations. Our high-resolution (10-km spacing) simulation predicts an equilibrium ice-shelf basal mass balance of −1648.7 Gt a−1 that increases to −1917.0 Gt a−1 when the observed ice-shelf thinning rates are taken into account. Our estimates reproduce the complexity of the basal mass balance of Antarctic ice shelves, providing a reference for parameterisations of sub-shelf ocean/ice interactions in continental ice-sheet models. We perform a sensitivity analysis to assess the effects of variations in the model set-up, showing that the retrieved estimates of basal melting and freezing rates are largely insensitive to changes in the internal model parameters, but respond strongly to a reduction of model resolution and the uncertainty in the input datasets.

scholarly journals On the effect of short-term climate variability on mountain glaciers: insights from a case study

2013 ◽  
Vol 59 (217) ◽  
pp. 992-1006 ◽  
Author(s):  
Daniel Farinotti
Keyword(s):  
Climatic Variability ◽  
Swiss Alps ◽  
Ice Dynamics ◽  
Mountain Glaciers ◽  
Temperature And Precipitation ◽  
Glacier Ice ◽  
Long Term Trends ◽  
Model Set ◽  
Set Up

AbstractStudies addressing the response of glaciers to climate change have so far analyzed the effect of long-term trends in a particular set of meteorological variables only, implicitly assuming an unaltered climatic variability. Here a framework for distinguishing between year-to-year, month-to-month and day-to-day variability is proposed. Synthetically generated temperature and precipitation time series following the same long-term trend but with altered variability are then used to force an ice-dynamics model set up for Rhonegletscher, Swiss Alps. In the case of temperature, variations in the day-to-day variability are shown to have a larger effect than changes at the yearly scale, while in the case of precipitation, variability changes are assessed as having negligible impact. A first set of scenarios is used to show that compared to reference, doubling the temperature variability can reduce glacier ice volume by up to 64% within half a decade. A second set derived from the results of the European ENSEMBLES project, however, shows that such changes are expected to remain below 8% even for extreme scenarios. Although the latter results relativize the importance of the effect in the near future, the analyses indicate that at least caution is required when assuming ‘unchanged variability’.

Sign in / Sign up

Export Citation Format

Share Document