scholarly journals Modeling Morphology With Linear Discriminative Learning: Considerations and Design Choices

2021 ◽  
Vol 12 ◽  
Author(s):  
Maria Heitmeier ◽  
Yu-Ying Chuang ◽  
R. Harald Baayen
Keyword(s):  
Incremental Learning ◽  
Model Performance ◽  
Discriminative Learning ◽  
Inflectional Morphology ◽  
Generalization Performance ◽  
Frequency Effects ◽  
Influence Model ◽  
Unseen Data ◽  
Set Up

This study addresses a series of methodological questions that arise when modeling inflectional morphology with Linear Discriminative Learning. Taking the semi-productive German noun system as example, we illustrate how decisions made about the representation of form and meaning influence model performance. We clarify that for modeling frequency effects in learning, it is essential to make use of incremental learning rather than the end-state of learning. We also discuss how the model can be set up to approximate the learning of inflected words in context. In addition, we illustrate how in this approach the wug task can be modeled. The model provides an excellent memory for known words, but appropriately shows more limited performance for unseen data, in line with the semi-productivity of German noun inflection and generalization performance of native German speakers.

scholarly journals Spatio-Temporal Hydrological Model Structure and Parametrization Analysis

2021 ◽  
Vol 9 (5) ◽  
pp. 467
Author(s):  
Mostafa Farrag ◽  
Gerald Corzo Perez ◽  
Dimitri Solomatine
Keyword(s):  
Hydrological Modeling ◽  
Model Building ◽  
Model Performance ◽  
Model Description ◽  
Generation Model ◽  
Model Structure ◽  
Runoff Generation ◽  
Spatial Sensitivity ◽  
Spatio Temporal ◽  
Set Up

Many grid-based spatial hydrological models suffer from the complexity of setting up a coherent spatial structure to calibrate such a complex, highly parameterized system. There are essential aspects of model-building to be taken into account: spatial resolution, the routing equation limitations, and calibration of spatial parameters, and their influence on modeling results, all are decisions that are often made without adequate analysis. In this research, an experimental analysis of grid discretization level, an analysis of processes integration, and the routing concepts are analyzed. The HBV-96 model is set up for each cell, and later on, cells are integrated into an interlinked modeling system (Hapi). The Jiboa River Basin in El Salvador is used as a case study. The first concept tested is the model structure temporal responses, which are highly linked to the runoff dynamics. By changing the runoff generation model description, we explore the responses to events. Two routing models are considered: Muskingum, which routes the runoff from each cell following the river network, and Maxbas, which routes the runoff directly to the outlet. The second concept is the spatial representation, where the model is built and tested for different spatial resolutions (500 m, 1 km, 2 km, and 4 km). The results show that the spatial sensitivity of the resolution is highly linked to the routing method, and it was found that routing sensitivity influenced the model performance more than the spatial discretization, and allowing for coarser discretization makes the model simpler and computationally faster. Slight performance improvement is gained by using different parameters’ values for each cell. It was found that the 2 km cell size corresponds to the least model error values. The proposed hydrological modeling codes have been published as open-source.

scholarly journals Putting Psychology to the Test: Rethinking Model Evaluation Through Benchmarking and Prediction

2021 ◽  
Vol 4 (3) ◽  
pp. 251524592110268
Author(s):  
Roberta Rocca ◽  
Tal Yarkoni
Keyword(s):  
Machine Learning ◽  
Performance Evaluation ◽  
Model Evaluation ◽  
Evaluation Criteria ◽  
Model Performance ◽  
Scientific Models ◽  
Practical Utility ◽  
Model Performance Evaluation ◽  
Unseen Data ◽  
Reliable Model

Consensus on standards for evaluating models and theories is an integral part of every science. Nonetheless, in psychology, relatively little focus has been placed on defining reliable communal metrics to assess model performance. Evaluation practices are often idiosyncratic and are affected by a number of shortcomings (e.g., failure to assess models’ ability to generalize to unseen data) that make it difficult to discriminate between good and bad models. Drawing inspiration from fields such as machine learning and statistical genetics, we argue in favor of introducing common benchmarks as a means of overcoming the lack of reliable model evaluation criteria currently observed in psychology. We discuss a number of principles benchmarks should satisfy to achieve maximal utility, identify concrete steps the community could take to promote the development of such benchmarks, and address a number of potential pitfalls and concerns that may arise in the course of implementation. We argue that reaching consensus on common evaluation benchmarks will foster cumulative progress in psychology and encourage researchers to place heavier emphasis on the practical utility of scientific models.

scholarly journals Technology adaptation of teachers and students under the learning continuity plan: A case of one school in the Philippines.

2021 ◽  
Vol 13 (4) ◽  
pp. 204-223
Author(s):  
Maricel Sacramento ◽  
Gina Ibanezr ◽  
MA. VICTORIA CASTILLO MAGAYON
Keyword(s):  
High School ◽  
Adaptive Learning ◽  
Model Performance ◽  
The Philippines ◽  
Senior High School ◽  
Technology Adaptation ◽  
Learning Modalities ◽  
Teachers And Students ◽  
Set Up ◽  
Remote Learning

The COVID-19 pandemic has prompted educational leaders to restructure the curriculum and modify the instructional set-up to accommodate remote learning of which using technology is the most viable solution to the existing problem. This study explores how teachers adapt and utilise technology-based teaching, and what makes students learn under blended learning modalities in Taytay Senior High School. Quantitatively, using the validated survey questionnaire anchored on the technology adaptation model and the adaptive learning environment model, this study revealed that teachers' age is the factor in all aspects of the model (performance and effort expectancy, social influence and facilitating conditions). When comparing the adaptation levels of students and teachers, it showed that teachers were slightly higher than the students, and that there is a negligible correlation. The findings of this study will serve as baseline data for immediate actions for items that surfaced concerns as hindrance or factors that can hamper students’ academic performance. Keywords: Technology adaptation, online classes, remote learning, Senior High School, Philippines.  

Discriminative Learning and the Lexicon: NDL and LDL

2021 ◽  
Author(s):  
Yu-Ying Chuang ◽  
R. Harald Baayen
Keyword(s):  
Lexical Processing ◽  
Morphological Processing ◽  
Discriminative Learning ◽  
Computational Algorithms ◽  
Association Strength ◽  
Computational Theory ◽  
Wide Range ◽  
Multivariate Multiple Regression ◽  
Lexical Learning ◽  
Set Up

Naive discriminative learning (NDL) and linear discriminative learning (LDL) are simple computational algorithms for lexical learning and lexical processing. Both NDL and LDL assume that learning is discriminative, driven by prediction error, and that it is this error that calibrates the association strength between input and output representations. Both words’ forms and their meanings are represented by numeric vectors, and mappings between forms and meanings are set up. For comprehension, form vectors predict meaning vectors. For production, meaning vectors map onto form vectors. These mappings can be learned incrementally, approximating how children learn the words of their language. Alternatively, optimal mappings representing the end state of learning can be estimated. The NDL and LDL algorithms are incorporated in a computational theory of the mental lexicon, the ‘discriminative lexicon’. The model shows good performance both with respect to production and comprehension accuracy, and for predicting aspects of lexical processing, including morphological processing, across a wide range of experiments. Since, mathematically, NDL and LDL implement multivariate multiple regression, the ‘discriminative lexicon’ provides a cognitively motivated statistical modeling approach to lexical processing.

scholarly journals Empirical Evaluation of the Effect of Optimization and Regularization Techniques on the Generalization Performance of Deep Convolutional Neural Network

2020 ◽  
Vol 10 (21) ◽  
pp. 7817
Author(s):  
Ivana Marin ◽  
Ana Kuzmanic Skelin ◽  
Tamara Grujic
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Convolutional Neural Network ◽  
Empirical Evaluation ◽  
Training Data ◽  
Generalization Performance ◽  
Deep Model ◽  
Unseen Data ◽  
Regularization Techniques ◽  
Learning Architectures

The main goal of any classification or regression task is to obtain a model that will generalize well on new, previously unseen data. Due to the recent rise of deep learning and many state-of-the-art results obtained with deep models, deep learning architectures have become one of the most used model architectures nowadays. To generalize well, a deep model needs to learn the training data well without overfitting. The latter implies a correlation of deep model optimization and regularization with generalization performance. In this work, we explore the effect of the used optimization algorithm and regularization techniques on the final generalization performance of the model with convolutional neural network (CNN) architecture widely used in the field of computer vision. We give a detailed overview of optimization and regularization techniques with a comparative analysis of their performance with three CNNs on the CIFAR-10 and Fashion-MNIST image datasets.

scholarly journals Using BiLSTM Networks for Context-Aware Deep Sensitivity Labelling on Conversational Data

2020 ◽  
Vol 10 (24) ◽  
pp. 8924
Author(s):  
Antreas Pogiatzis ◽  
Georgios Samakovitis
Keyword(s):  
Conditional Random Fields ◽  
Short Term Memory ◽  
Model Performance ◽  
Design Feature ◽  
Sensitive Information ◽  
Context Aware ◽  
Improve Model ◽  
Unseen Data ◽  
Memory Network ◽  
Series Of Experiments

Information privacy is a critical design feature for any exchange system, with privacy-preserving applications requiring, most of the time, the identification and labelling of sensitive information. However, privacy and the concept of “sensitive information” are extremely elusive terms, as they are heavily dependent upon the context they are conveyed in. To accommodate such specificity, we first introduce a taxonomy of four context classes to categorise relationships of terms with their textual surroundings by meaning, interaction, precedence, and preference. We then propose a predictive context-aware model based on a Bidirectional Long Short Term Memory network with Conditional Random Fields (BiLSTM + CRF) to identify and label sensitive information in conversational data (multi-class sensitivity labelling). We train our model on a synthetic annotated dataset of real-world conversational data categorised in 13 sensitivity classes that we derive from the P3P standard. We parameterise and run a series of experiments featuring word and character embeddings and introduce a set of auxiliary features to improve model performance. Our results demonstrate that the BiLSTM + CRF model architecture with BERT embeddings and WordShape features is the most effective (F1 score 96.73%). Evaluation of the model is conducted under both temporal and semantic contexts, achieving a 76.33% F1 score on unseen data and outperforms Google’s Data Loss Prevention (DLP) system on sensitivity labelling tasks.

scholarly journals Using the Soil and Water Assessment Tool to Simulate the Pesticide Dynamics in the Data Scarce Guayas River Basin, Ecuador

Water ◽  
2020 ◽  
Vol 12 (3) ◽  
pp. 696 ◽  
Author(s):  
Naomi Cambien ◽  
Sacha Gobeyn ◽  
Indira Nolivos ◽  
Marie Anne Eurie Forio ◽  
Mijail Arias-Hidalgo ◽  
...  
Keyword(s):  
River Basin ◽  
Assessment Tool ◽  
Model Development ◽  
Model Performance ◽  
Water Quality Monitoring ◽  
Freshwater Ecosystem ◽  
Set Up ◽  
The Impact ◽  
Water Assessment ◽  
Soil And Water

Agricultural intensification has stimulated the economy in the Guayas River basin in Ecuador, but also affected several ecosystems. The increased use of pesticides poses a serious threat to the freshwater ecosystem, which urgently calls for an improved knowledge about the impact of pesticide practices in this study area. Several studies have shown that models can be appropriate tools to simulate pesticide dynamics in order to obtain this knowledge. This study tested the suitability of the Soil and Water Assessment Tool (SWAT) to simulate the dynamics of two different pesticides in the data scarce Guayas River basin. First, we set up, calibrated and validated the model using the streamflow data. Subsequently, we set up the model for the simulation of the selected pesticides (i.e., pendimethalin and fenpropimorph). While the hydrology was represented soundly by the model considering the data scare conditions, the simulation of the pesticides should be taken with care due to uncertainties behind essential drivers, e.g., application rates. Among the insights obtained from the pesticide simulations are the identification of critical zones for prioritisation, the dominant areas of pesticide sources and the impact of the different land uses. SWAT has been evaluated to be a suitable tool to investigate the impact of pesticide use under data scarcity in the Guayas River basin. The strengths of SWAT are its semi-distributed structure, availability of extensive online documentation, internal pesticide databases and user support while the limitations are high data requirements, time-intensive model development and challenging streamflow calibration. The results can also be helpful to design future water quality monitoring strategies. However, for future studies, we highly recommend extended monitoring of pesticide concentrations and sediment loads. Moreover, to substantially improve the model performance, the availability of better input data is needed such as higher resolution soil maps, more accurate pesticide application rate and actual land management programs. Provided that key suggestions for further improvement are considered, the model is valuable for applications in river ecosystem management of the Guayas River basin.

Statistical Translation After Source Reordering: Oracles, Context-Aware Models, and Empirical Analysis

2012 ◽  
Vol 18 (4) ◽  
pp. 491-519 ◽  
Author(s):  
MAXIM KHALILOV ◽  
KHALIL SIMA'AN
Keyword(s):  
Word Order ◽  
Target Sentence ◽  
Training Data ◽  
Translation System ◽  
Long Distance ◽  
Translation Model ◽  
Unseen Data ◽  
Carry Over ◽  
Set Up ◽  
The Impact

AbstractIn source reordering the order of the source words is permuted to minimize word order differences with the target sentence and then fed to a translation model. Earlier work highlights the benefits of resolving long-distance reorderings as a pre-processing step to standard phrase-based models. However, the potential performance improvement of source reordering and its impact on the components of the subsequent translation model remain unexplored. In this paper we study both aspects of source reordering. We set up idealized source reordering (oracle) models with/without syntax and present our own syntax-driven model of source reordering. The latter is a statistical model of inversion transduction grammar (ITG)-like tree transductions manipulating a syntactic parse and working with novel conditional reordering parameters. Having set up the models, we report translation experiments showing significant improvement on three language pairs, and contribute an extensive analysis of the impact of source reordering (both oracle and model) on the translation model regarding the quality of its input, phrase-table, and output. Our experiments show that oracle source reordering has untapped potential in improving translation system output. Besides solving difficult reorderings, we find that source reordering creates more monotone parallel training data at the back-end, leading to significantly larger phrase tables with higher coverage of phrase types in unseen data. Unfortunately, this nice property does not carry over to tree-constrained source reordering. Our analysis shows that, from the string-level perspective, tree-constrained reordering might selectively permute word order, leading to larger phrase tables but without increase in phrase coverage in unseen data.

Sign in / Sign up

Export Citation Format

Share Document