scholarly journals Document Re-Ranking Model for Machine-Reading and Comprehension

2020 ◽  
Vol 10 (21) ◽  
pp. 7547
Author(s):  
Youngjin Jang ◽  
Harksoo Kim
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
High Performance ◽  
Language Model ◽  
Text Retrieval ◽  
Retrieval Models ◽  
Similarity Network ◽  
Proposed Model ◽  
Ranking Model ◽  
Machine Reading

Recently, the performance of machine-reading and comprehension (MRC) systems has been significantly enhanced. However, MRC systems require high-performance text retrieval models because text passages containing answer phrases should be prepared in advance. To improve the performance of text retrieval models underlying MRC systems, we propose a re-ranking model, based on artificial neural networks, that is composed of a query encoder, a passage encoder, a phrase modeling layer, an attention layer, and a similarity network. The proposed model learns degrees of associations between queries and text passages through dot products between phrases that constitute questions and passages. In experiments with the MS-MARCO dataset, the proposed model demonstrated higher mean reciprocal ranks (MRRs), 0.8%p–13.2%p, than most of the previous models, except for the models based on BERT (a pre-trained language model). Although the proposed model demonstrated lower MRRs than the BERT-based models, it was approximately 8 times lighter and 3.7 times faster than the BERT-based models.

Investigating of Correlation between MODIS Satellite Data and Ground Data Related to Aerosols and Modeling Aerosols Using Neural Networks over Shiraz

2012 ◽  
Vol 260-261 ◽  
pp. 926-929
Author(s):  
Ali Reza Dehghani ◽  
Ali Akbar Safavi ◽  
Mohammad Jafar Nazemossadat ◽  
Seyed Mohammad Hessam Mohammadi
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Satellite Data ◽  
Satellite Image ◽  
Frequency Bands ◽  
Input And Output ◽  
Satellite Information ◽  
Proposed Model ◽  
Artificial Neural ◽  
Band Number

This paper presents an investigation of satellite data and ground data about aerosols and then modelsthe mentioned data over Shiraz using artificial neural networks. MODIS satellite data are available on 36 various frequency bands. In this study, a good correlation between ground data and the 10 first satellite image bands is being shown. Specially, the best correlation was found in band number 8. Therefore, using neural networks and ground data along with satellite information, a model of aerosols is constructed. In the mentioned model, satellite data of band 8 and ground data are used as network input and output, respectively. The results show the effectiveness of the proposed model.

scholarly journals Metamodel for nodal pressure estimation at near real-time in water distribution systems using artificial neural networks

2017 ◽  
Vol 20 (2) ◽  
pp. 486-496 ◽  
Author(s):  
Gustavo Meirelles Lima ◽  
Bruno Melo Brentan ◽  
Daniel Manzi ◽  
Edevar Luvizotto
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Distribution Systems ◽  
Water Distribution ◽  
Computational Models ◽  
Pressure Sensors ◽  
Water Supply Systems ◽  
Pressure Data ◽  
Proposed Model ◽  
Artificial Neural

Abstract The development of computational models for analysis of the operation of water supply systems requires the calibration of pipes' roughness, among other parameters. Inadequate values of this parameter can result in inaccurate solutions, compromising the applicability of the model as a decision-making tool. This paper presents a metamodel to estimate the pressure at all nodes of a distribution network based on artificial neural networks (ANNs), using a set of field data obtained from strategically located pressure sensors. This approach aims to increase the available pressure data, reducing the degree of freedom of the calibration problem. The proposed model uses the inlet flow of the district metering area and pressure data monitored in some nodes, as input data to the ANN, obtaining as output, the pressure values for nodes that were not monitored. Two case studies of real networks are presented to validate the efficiency and accuracy of the method. The results ratify the efficiency of ANN as state forecaster, showing the high applicability of the metamodel tool to increase a database or to identify abnormal events during an operation.

scholarly journals Deep Learning and Autoregressive Approach for Prediction of Time Series Data

2021 ◽  
Vol 3 (2) ◽  
pp. 1
Author(s):  
Akhter Mohiuddin Rather
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Deep Learning ◽  
Statistical Models ◽  
Time Complexity ◽  
Time Series Data ◽  
Series Data ◽  
Learning Approach ◽  
Proposed Model ◽  
Artificial Neural

Fractional This paper proposes a deep learning approach for prediction of nonstationary data. A new regression scheme has been used in the proposed model. Any non-stationary data can be used to test the efficiency of the proposed model, however in this work stock data has been used due to the fact that stock data has a property of being nonlinear or non-stationary in nature. Beside using proposed model, predictions were also obtained using some statistical models and artificial neural networks. Traditional statistical models did not yield any expected results; artificial neural networks resulted into high time complexity. Therefore, deep learning approach seemed to be the best method as of today in dealing with such problems wherein time complexity and excellent predictions are of concern.

scholarly journals Semantic Systematicity in Connectionist Language Production

Information ◽  
2021 ◽  
Vol 12 (8) ◽  
pp. 329
Author(s):  
Jesús Calvillo ◽  
Harm Brouwer ◽  
Matthew W. Crocker
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Artificial Neural Networks ◽  
Language Production ◽  
High Performance ◽  
Situation Model ◽  
Sentence Production ◽  
Connectionist Model ◽  
The Neural Network ◽  
Positive Results

Decades of studies trying to define the extent to which artificial neural networks can exhibit systematicity suggest that systematicity can be achieved by connectionist models but not by default. Here we present a novel connectionist model of sentence production that employs rich situation model representations originally proposed for modeling systematicity in comprehension. The high performance of our model demonstrates that such representations are also well suited to model language production. Furthermore, the model can produce multiple novel sentences for previously unseen situations, including in a different voice (actives vs. passive) and with words in new syntactic roles, thus demonstrating semantic and syntactic generalization and arguably systematicity. Our results provide yet further evidence that such connectionist approaches can achieve systematicity, in production as well as comprehension. We propose our positive results to be a consequence of the regularities of the microworld from which the semantic representations are derived, which provides a sufficient structure from which the neural network can interpret novel inputs.

scholarly journals Predicting the Cardioactivity of Tivela stultorum clam with Digoxin Using Artificial Neural Networks

2017 ◽  
Author(s):  
◽  
D. Flores
Keyword(s):  
Neural Networks ◽  
Heart Rate ◽  
Artificial Neural Networks ◽  
High Performance ◽  
Digoxin Concentration ◽  
Computational Method ◽  
Specific Concentration ◽  
Filling Time ◽  
Artificial Neural

Artificial neural networks (ANN) are a computational method that has been widely used to solve complex problems and carry out predictions on nonlinear systems. Multilayer perceptron artificial neural networks were used to predict the physiological response that would be obtained by adding a specific concentration of digoxin to Tivela stultorum hearts, this organism is a model for testing cardiac drugs that pretends to be used in humans. The MLPANN inputs were weight, volume, length, and width of the heart, digoxin concentration and volume used for diluting digoxin, and maximum contraction, minimum contraction, filling time, and heart rate before adding digoxin, and the outputs were the maximum contraction, minimum contraction, filling time, and heart rate that would be obtained after adding digoxin to the heart. ANNs were trained, validated, and tested with the results obtained from the in vivo experiments. To choose the optimal network, the smallest square mean error value was used. Perceptrons obtained a high performance and correlation between predicted and calculated values, except in the case of the filling time output. Accurate predictions of the T. stultorum clams cardioactivity were obtained when a specific concentration of digoxin was added using ANNs with one hidden layer; this could be useful as a tool to facilitate laboratory experiments to test digoxin effects.

Sign in / Sign up

Export Citation Format

Share Document